Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
15a90bf
•
1 Parent(s): 791a163

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 +242 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631b45bd8f9c6866dba541f08e6bcdb6c56f0fbc3c8fd6405170a7a335118d41
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 15:43:51 0.0000 0.4876 0.1395 0.6353 0.7423 0.6846 0.5562
3
+ 2 15:45:13 0.0000 0.1366 0.1482 0.7718 0.7944 0.7830 0.6723
4
+ 3 15:46:33 0.0000 0.0916 0.1663 0.7827 0.7858 0.7842 0.6779
5
+ 4 15:47:56 0.0000 0.0658 0.1763 0.8139 0.8167 0.8153 0.7123
6
+ 5 15:49:18 0.0000 0.0484 0.1882 0.7853 0.8150 0.7999 0.6914
7
+ 6 15:50:39 0.0000 0.0328 0.2048 0.7843 0.8225 0.8029 0.7005
8
+ 7 15:52:00 0.0000 0.0231 0.2176 0.7987 0.8225 0.8104 0.7116
9
+ 8 15:53:22 0.0000 0.0173 0.2092 0.8034 0.8333 0.8181 0.7217
10
+ 9 15:54:43 0.0000 0.0115 0.2227 0.8093 0.8213 0.8152 0.7177
11
+ 10 15:56:05 0.0000 0.0060 0.2283 0.8091 0.8253 0.8171 0.7191
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 15:42:35,866 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 15:42:35,867 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 15:42:35,867 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 15:42:35,867 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 15:42:35,867 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 15:42:35,867 Train: 5901 sentences
55
+ 2023-10-13 15:42:35,867 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 15:42:35,867 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 15:42:35,867 Training Params:
58
+ 2023-10-13 15:42:35,867 - learning_rate: "5e-05"
59
+ 2023-10-13 15:42:35,867 - mini_batch_size: "4"
60
+ 2023-10-13 15:42:35,868 - max_epochs: "10"
61
+ 2023-10-13 15:42:35,868 - shuffle: "True"
62
+ 2023-10-13 15:42:35,868 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 15:42:35,868 Plugins:
64
+ 2023-10-13 15:42:35,868 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 15:42:35,868 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 15:42:35,868 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 15:42:35,868 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 15:42:35,868 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 15:42:35,868 Computation:
70
+ 2023-10-13 15:42:35,868 - compute on device: cuda:0
71
+ 2023-10-13 15:42:35,868 - embedding storage: none
72
+ 2023-10-13 15:42:35,868 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 15:42:35,868 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 15:42:35,868 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 15:42:35,868 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 15:42:42,852 epoch 1 - iter 147/1476 - loss 2.30028384 - time (sec): 6.98 - samples/sec: 2417.10 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 15:42:49,682 epoch 1 - iter 294/1476 - loss 1.45013254 - time (sec): 13.81 - samples/sec: 2399.46 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 15:42:57,042 epoch 1 - iter 441/1476 - loss 1.06928097 - time (sec): 21.17 - samples/sec: 2472.20 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 15:43:03,830 epoch 1 - iter 588/1476 - loss 0.89478293 - time (sec): 27.96 - samples/sec: 2410.19 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 15:43:10,679 epoch 1 - iter 735/1476 - loss 0.77703571 - time (sec): 34.81 - samples/sec: 2401.38 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-13 15:43:17,429 epoch 1 - iter 882/1476 - loss 0.69040845 - time (sec): 41.56 - samples/sec: 2383.42 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-13 15:43:24,222 epoch 1 - iter 1029/1476 - loss 0.62755418 - time (sec): 48.35 - samples/sec: 2364.76 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-13 15:43:30,951 epoch 1 - iter 1176/1476 - loss 0.57577336 - time (sec): 55.08 - samples/sec: 2354.56 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-13 15:43:38,279 epoch 1 - iter 1323/1476 - loss 0.52275812 - time (sec): 62.41 - samples/sec: 2389.60 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-13 15:43:45,281 epoch 1 - iter 1470/1476 - loss 0.48888637 - time (sec): 69.41 - samples/sec: 2388.74 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-13 15:43:45,558 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 15:43:45,558 EPOCH 1 done: loss 0.4876 - lr: 0.000050
88
+ 2023-10-13 15:43:51,735 DEV : loss 0.13950972259044647 - f1-score (micro avg) 0.6846
89
+ 2023-10-13 15:43:51,763 saving best model
90
+ 2023-10-13 15:43:52,181 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 15:43:59,160 epoch 2 - iter 147/1476 - loss 0.15312363 - time (sec): 6.98 - samples/sec: 2436.22 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 15:44:05,796 epoch 2 - iter 294/1476 - loss 0.14515788 - time (sec): 13.61 - samples/sec: 2295.82 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 15:44:12,599 epoch 2 - iter 441/1476 - loss 0.14926136 - time (sec): 20.42 - samples/sec: 2289.42 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 15:44:19,464 epoch 2 - iter 588/1476 - loss 0.14665798 - time (sec): 27.28 - samples/sec: 2311.85 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 15:44:26,111 epoch 2 - iter 735/1476 - loss 0.14371952 - time (sec): 33.93 - samples/sec: 2309.91 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 15:44:34,075 epoch 2 - iter 882/1476 - loss 0.14402450 - time (sec): 41.89 - samples/sec: 2392.34 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 15:44:41,076 epoch 2 - iter 1029/1476 - loss 0.14095397 - time (sec): 48.89 - samples/sec: 2394.34 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 15:44:47,968 epoch 2 - iter 1176/1476 - loss 0.14022068 - time (sec): 55.79 - samples/sec: 2387.41 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 15:44:54,873 epoch 2 - iter 1323/1476 - loss 0.13964413 - time (sec): 62.69 - samples/sec: 2391.33 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 15:45:01,710 epoch 2 - iter 1470/1476 - loss 0.13667497 - time (sec): 69.53 - samples/sec: 2385.92 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-13 15:45:01,973 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 15:45:01,974 EPOCH 2 done: loss 0.1366 - lr: 0.000044
103
+ 2023-10-13 15:45:13,154 DEV : loss 0.14815327525138855 - f1-score (micro avg) 0.783
104
+ 2023-10-13 15:45:13,184 saving best model
105
+ 2023-10-13 15:45:13,775 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 15:45:20,684 epoch 3 - iter 147/1476 - loss 0.08626971 - time (sec): 6.90 - samples/sec: 2220.34 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 15:45:27,452 epoch 3 - iter 294/1476 - loss 0.08510510 - time (sec): 13.67 - samples/sec: 2295.99 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 15:45:34,356 epoch 3 - iter 441/1476 - loss 0.09017739 - time (sec): 20.58 - samples/sec: 2360.38 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 15:45:41,425 epoch 3 - iter 588/1476 - loss 0.09251949 - time (sec): 27.64 - samples/sec: 2381.15 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 15:45:48,404 epoch 3 - iter 735/1476 - loss 0.09530762 - time (sec): 34.62 - samples/sec: 2408.54 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 15:45:54,862 epoch 3 - iter 882/1476 - loss 0.09482173 - time (sec): 41.08 - samples/sec: 2397.41 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 15:46:01,516 epoch 3 - iter 1029/1476 - loss 0.09283997 - time (sec): 47.74 - samples/sec: 2417.28 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 15:46:08,514 epoch 3 - iter 1176/1476 - loss 0.09432800 - time (sec): 54.73 - samples/sec: 2414.61 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 15:46:15,114 epoch 3 - iter 1323/1476 - loss 0.09378249 - time (sec): 61.33 - samples/sec: 2424.67 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-13 15:46:22,293 epoch 3 - iter 1470/1476 - loss 0.09168940 - time (sec): 68.51 - samples/sec: 2422.02 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 15:46:22,555 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 15:46:22,556 EPOCH 3 done: loss 0.0916 - lr: 0.000039
118
+ 2023-10-13 15:46:33,729 DEV : loss 0.16625124216079712 - f1-score (micro avg) 0.7842
119
+ 2023-10-13 15:46:33,759 saving best model
120
+ 2023-10-13 15:46:34,290 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 15:46:40,939 epoch 4 - iter 147/1476 - loss 0.05685033 - time (sec): 6.65 - samples/sec: 2384.08 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 15:46:48,069 epoch 4 - iter 294/1476 - loss 0.06479773 - time (sec): 13.78 - samples/sec: 2436.98 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 15:46:55,648 epoch 4 - iter 441/1476 - loss 0.06082232 - time (sec): 21.35 - samples/sec: 2464.05 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 15:47:02,562 epoch 4 - iter 588/1476 - loss 0.06505374 - time (sec): 28.27 - samples/sec: 2398.45 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 15:47:09,655 epoch 4 - iter 735/1476 - loss 0.06490679 - time (sec): 35.36 - samples/sec: 2358.79 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 15:47:16,482 epoch 4 - iter 882/1476 - loss 0.06350270 - time (sec): 42.19 - samples/sec: 2323.62 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 15:47:23,844 epoch 4 - iter 1029/1476 - loss 0.06399013 - time (sec): 49.55 - samples/sec: 2342.65 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 15:47:30,580 epoch 4 - iter 1176/1476 - loss 0.06430831 - time (sec): 56.29 - samples/sec: 2330.72 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-13 15:47:37,629 epoch 4 - iter 1323/1476 - loss 0.06572771 - time (sec): 63.33 - samples/sec: 2354.52 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 15:47:44,586 epoch 4 - iter 1470/1476 - loss 0.06583572 - time (sec): 70.29 - samples/sec: 2359.14 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 15:47:44,847 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 15:47:44,848 EPOCH 4 done: loss 0.0658 - lr: 0.000033
133
+ 2023-10-13 15:47:56,082 DEV : loss 0.17630523443222046 - f1-score (micro avg) 0.8153
134
+ 2023-10-13 15:47:56,112 saving best model
135
+ 2023-10-13 15:47:56,711 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 15:48:03,253 epoch 5 - iter 147/1476 - loss 0.04485170 - time (sec): 6.54 - samples/sec: 2355.16 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 15:48:09,999 epoch 5 - iter 294/1476 - loss 0.03902816 - time (sec): 13.28 - samples/sec: 2369.02 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 15:48:17,002 epoch 5 - iter 441/1476 - loss 0.04504258 - time (sec): 20.29 - samples/sec: 2406.17 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 15:48:23,884 epoch 5 - iter 588/1476 - loss 0.04251002 - time (sec): 27.17 - samples/sec: 2378.67 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 15:48:31,087 epoch 5 - iter 735/1476 - loss 0.04220286 - time (sec): 34.37 - samples/sec: 2391.39 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 15:48:38,154 epoch 5 - iter 882/1476 - loss 0.04528667 - time (sec): 41.44 - samples/sec: 2388.13 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 15:48:45,300 epoch 5 - iter 1029/1476 - loss 0.04637233 - time (sec): 48.59 - samples/sec: 2356.76 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-13 15:48:52,720 epoch 5 - iter 1176/1476 - loss 0.04767054 - time (sec): 56.01 - samples/sec: 2372.28 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 15:48:59,761 epoch 5 - iter 1323/1476 - loss 0.04742459 - time (sec): 63.05 - samples/sec: 2367.60 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 15:49:06,688 epoch 5 - iter 1470/1476 - loss 0.04806456 - time (sec): 69.97 - samples/sec: 2371.06 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 15:49:06,946 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 15:49:06,947 EPOCH 5 done: loss 0.0484 - lr: 0.000028
148
+ 2023-10-13 15:49:18,117 DEV : loss 0.18819278478622437 - f1-score (micro avg) 0.7999
149
+ 2023-10-13 15:49:18,147 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 15:49:25,047 epoch 6 - iter 147/1476 - loss 0.03631651 - time (sec): 6.90 - samples/sec: 2179.78 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-13 15:49:31,878 epoch 6 - iter 294/1476 - loss 0.03341746 - time (sec): 13.73 - samples/sec: 2233.74 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 15:49:39,202 epoch 6 - iter 441/1476 - loss 0.03106010 - time (sec): 21.05 - samples/sec: 2342.54 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-13 15:49:46,275 epoch 6 - iter 588/1476 - loss 0.03516578 - time (sec): 28.13 - samples/sec: 2336.61 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 15:49:53,144 epoch 6 - iter 735/1476 - loss 0.03483987 - time (sec): 35.00 - samples/sec: 2348.33 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-13 15:50:00,155 epoch 6 - iter 882/1476 - loss 0.03313512 - time (sec): 42.01 - samples/sec: 2372.38 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-13 15:50:06,939 epoch 6 - iter 1029/1476 - loss 0.03286769 - time (sec): 48.79 - samples/sec: 2353.00 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-13 15:50:13,772 epoch 6 - iter 1176/1476 - loss 0.03254763 - time (sec): 55.62 - samples/sec: 2356.11 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-13 15:50:21,043 epoch 6 - iter 1323/1476 - loss 0.03345823 - time (sec): 62.89 - samples/sec: 2387.16 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 15:50:27,847 epoch 6 - iter 1470/1476 - loss 0.03287175 - time (sec): 69.70 - samples/sec: 2380.16 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-13 15:50:28,118 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 15:50:28,119 EPOCH 6 done: loss 0.0328 - lr: 0.000022
162
+ 2023-10-13 15:50:39,277 DEV : loss 0.20484893023967743 - f1-score (micro avg) 0.8029
163
+ 2023-10-13 15:50:39,307 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-13 15:50:46,072 epoch 7 - iter 147/1476 - loss 0.01775270 - time (sec): 6.76 - samples/sec: 2267.31 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-13 15:50:53,821 epoch 7 - iter 294/1476 - loss 0.02118488 - time (sec): 14.51 - samples/sec: 2336.41 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-13 15:51:00,455 epoch 7 - iter 441/1476 - loss 0.02237123 - time (sec): 21.15 - samples/sec: 2323.11 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 15:51:07,535 epoch 7 - iter 588/1476 - loss 0.02143611 - time (sec): 28.23 - samples/sec: 2322.19 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-13 15:51:14,428 epoch 7 - iter 735/1476 - loss 0.02320718 - time (sec): 35.12 - samples/sec: 2341.16 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-13 15:51:21,513 epoch 7 - iter 882/1476 - loss 0.02422687 - time (sec): 42.21 - samples/sec: 2384.20 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-13 15:51:28,587 epoch 7 - iter 1029/1476 - loss 0.02343024 - time (sec): 49.28 - samples/sec: 2402.37 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-13 15:51:35,674 epoch 7 - iter 1176/1476 - loss 0.02306815 - time (sec): 56.37 - samples/sec: 2392.98 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 15:51:42,416 epoch 7 - iter 1323/1476 - loss 0.02322261 - time (sec): 63.11 - samples/sec: 2374.09 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-13 15:51:49,345 epoch 7 - iter 1470/1476 - loss 0.02302954 - time (sec): 70.04 - samples/sec: 2368.47 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 15:51:49,612 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-13 15:51:49,612 EPOCH 7 done: loss 0.0231 - lr: 0.000017
176
+ 2023-10-13 15:52:00,780 DEV : loss 0.2176404744386673 - f1-score (micro avg) 0.8104
177
+ 2023-10-13 15:52:00,810 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-13 15:52:07,878 epoch 8 - iter 147/1476 - loss 0.01220283 - time (sec): 7.07 - samples/sec: 2310.70 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-13 15:52:14,683 epoch 8 - iter 294/1476 - loss 0.01477755 - time (sec): 13.87 - samples/sec: 2316.37 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-13 15:52:21,717 epoch 8 - iter 441/1476 - loss 0.01557002 - time (sec): 20.91 - samples/sec: 2387.69 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-13 15:52:28,637 epoch 8 - iter 588/1476 - loss 0.01728477 - time (sec): 27.83 - samples/sec: 2368.74 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-13 15:52:35,625 epoch 8 - iter 735/1476 - loss 0.01772118 - time (sec): 34.81 - samples/sec: 2350.82 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-13 15:52:42,709 epoch 8 - iter 882/1476 - loss 0.01840414 - time (sec): 41.90 - samples/sec: 2332.60 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-13 15:52:49,619 epoch 8 - iter 1029/1476 - loss 0.01749539 - time (sec): 48.81 - samples/sec: 2327.72 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-13 15:52:57,024 epoch 8 - iter 1176/1476 - loss 0.01800568 - time (sec): 56.21 - samples/sec: 2344.29 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-13 15:53:03,895 epoch 8 - iter 1323/1476 - loss 0.01708246 - time (sec): 63.08 - samples/sec: 2351.96 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-13 15:53:10,882 epoch 8 - iter 1470/1476 - loss 0.01733501 - time (sec): 70.07 - samples/sec: 2368.38 - lr: 0.000011 - momentum: 0.000000
188
+ 2023-10-13 15:53:11,151 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-13 15:53:11,151 EPOCH 8 done: loss 0.0173 - lr: 0.000011
190
+ 2023-10-13 15:53:22,272 DEV : loss 0.20916695892810822 - f1-score (micro avg) 0.8181
191
+ 2023-10-13 15:53:22,301 saving best model
192
+ 2023-10-13 15:53:22,822 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-13 15:53:29,893 epoch 9 - iter 147/1476 - loss 0.01635506 - time (sec): 7.07 - samples/sec: 2461.72 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-13 15:53:36,767 epoch 9 - iter 294/1476 - loss 0.01655047 - time (sec): 13.94 - samples/sec: 2426.64 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-13 15:53:43,754 epoch 9 - iter 441/1476 - loss 0.01517177 - time (sec): 20.93 - samples/sec: 2367.10 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-13 15:53:50,701 epoch 9 - iter 588/1476 - loss 0.01363129 - time (sec): 27.88 - samples/sec: 2364.14 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-13 15:53:57,583 epoch 9 - iter 735/1476 - loss 0.01340167 - time (sec): 34.76 - samples/sec: 2360.92 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-13 15:54:04,370 epoch 9 - iter 882/1476 - loss 0.01292839 - time (sec): 41.54 - samples/sec: 2347.88 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-13 15:54:11,324 epoch 9 - iter 1029/1476 - loss 0.01181704 - time (sec): 48.50 - samples/sec: 2370.28 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-13 15:54:18,449 epoch 9 - iter 1176/1476 - loss 0.01179880 - time (sec): 55.62 - samples/sec: 2378.75 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-13 15:54:25,296 epoch 9 - iter 1323/1476 - loss 0.01152101 - time (sec): 62.47 - samples/sec: 2384.12 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-13 15:54:32,279 epoch 9 - iter 1470/1476 - loss 0.01152718 - time (sec): 69.45 - samples/sec: 2389.38 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-13 15:54:32,541 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-13 15:54:32,541 EPOCH 9 done: loss 0.0115 - lr: 0.000006
205
+ 2023-10-13 15:54:43,751 DEV : loss 0.22271640598773956 - f1-score (micro avg) 0.8152
206
+ 2023-10-13 15:54:43,780 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-13 15:54:50,626 epoch 10 - iter 147/1476 - loss 0.01146130 - time (sec): 6.84 - samples/sec: 2359.28 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-13 15:54:58,158 epoch 10 - iter 294/1476 - loss 0.00823611 - time (sec): 14.38 - samples/sec: 2480.56 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-13 15:55:05,151 epoch 10 - iter 441/1476 - loss 0.00776873 - time (sec): 21.37 - samples/sec: 2419.29 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-13 15:55:12,220 epoch 10 - iter 588/1476 - loss 0.00660613 - time (sec): 28.44 - samples/sec: 2368.38 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 15:55:18,963 epoch 10 - iter 735/1476 - loss 0.00628384 - time (sec): 35.18 - samples/sec: 2351.18 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-13 15:55:25,778 epoch 10 - iter 882/1476 - loss 0.00654294 - time (sec): 42.00 - samples/sec: 2333.14 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 15:55:33,071 epoch 10 - iter 1029/1476 - loss 0.00618452 - time (sec): 49.29 - samples/sec: 2340.88 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 15:55:40,251 epoch 10 - iter 1176/1476 - loss 0.00649196 - time (sec): 56.47 - samples/sec: 2335.05 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 15:55:47,188 epoch 10 - iter 1323/1476 - loss 0.00610162 - time (sec): 63.41 - samples/sec: 2332.22 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 15:55:54,348 epoch 10 - iter 1470/1476 - loss 0.00601101 - time (sec): 70.57 - samples/sec: 2353.06 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-13 15:55:54,607 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-13 15:55:54,607 EPOCH 10 done: loss 0.0060 - lr: 0.000000
219
+ 2023-10-13 15:56:05,754 DEV : loss 0.22833691537380219 - f1-score (micro avg) 0.8171
220
+ 2023-10-13 15:56:06,208 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-13 15:56:06,209 Loading model from best epoch ...
222
+ 2023-10-13 15:56:07,748 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
223
+ 2023-10-13 15:56:13,701
224
+ Results:
225
+ - F-score (micro) 0.7761
226
+ - F-score (macro) 0.6771
227
+ - Accuracy 0.6563
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.8328 0.8590 0.8457 858
233
+ pers 0.7347 0.7840 0.7586 537
234
+ org 0.5094 0.6136 0.5567 132
235
+ time 0.5397 0.6296 0.5812 54
236
+ prod 0.6852 0.6066 0.6435 61
237
+
238
+ micro avg 0.7555 0.7978 0.7761 1642
239
+ macro avg 0.6604 0.6986 0.6771 1642
240
+ weighted avg 0.7596 0.7978 0.7777 1642
241
+
242
+ 2023-10-13 15:56:13,701 ----------------------------------------------------------------------------------------------------