Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
fc59905
•
1 Parent(s): 48da97f

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697586384.bce904bcef33.2482.19 +3 -0
  5. test.tsv +0 -0
  6. training.log +242 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3300f3334aaf15ba1fdeb04a694296207cd7012b971d949d8c8f51b9ef7dc0
3
+ size 440966725
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 23:47:43 0.0000 0.4841 0.2155 0.6937 0.7291 0.7110 0.5724
3
+ 2 23:49:07 0.0000 0.1399 0.1417 0.7431 0.8351 0.7864 0.6734
4
+ 3 23:50:32 0.0000 0.0934 0.1794 0.7624 0.8087 0.7849 0.6785
5
+ 4 23:51:59 0.0000 0.0635 0.1764 0.8085 0.8196 0.8140 0.7134
6
+ 5 23:53:24 0.0000 0.0442 0.1814 0.8076 0.8414 0.8241 0.7236
7
+ 6 23:54:50 0.0000 0.0275 0.2117 0.8093 0.8288 0.8189 0.7199
8
+ 7 23:56:15 0.0000 0.0225 0.2210 0.8232 0.8345 0.8288 0.7263
9
+ 8 23:57:39 0.0000 0.0125 0.2112 0.8421 0.8494 0.8457 0.7516
10
+ 9 23:59:02 0.0000 0.0082 0.2453 0.8493 0.8362 0.8427 0.7495
11
+ 10 00:00:26 0.0000 0.0042 0.2396 0.8535 0.8442 0.8488 0.7547
runs/events.out.tfevents.1697586384.bce904bcef33.2482.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc728fe87f2448acd438806a1e6e935a6c06465e9e773c449343a108dd067572
3
+ size 825716
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 23:46:24,650 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 23:46:24,651 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
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): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
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): ElectraSelfOutput(
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): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
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
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=21, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 23:46:24,651 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 23:46:24,651 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
48
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
49
+ 2023-10-17 23:46:24,651 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 23:46:24,651 Train: 5901 sentences
51
+ 2023-10-17 23:46:24,651 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 23:46:24,651 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 23:46:24,651 Training Params:
54
+ 2023-10-17 23:46:24,651 - learning_rate: "5e-05"
55
+ 2023-10-17 23:46:24,651 - mini_batch_size: "4"
56
+ 2023-10-17 23:46:24,651 - max_epochs: "10"
57
+ 2023-10-17 23:46:24,651 - shuffle: "True"
58
+ 2023-10-17 23:46:24,651 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 23:46:24,651 Plugins:
60
+ 2023-10-17 23:46:24,651 - TensorboardLogger
61
+ 2023-10-17 23:46:24,651 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 23:46:24,651 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 23:46:24,652 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 23:46:24,652 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 23:46:24,652 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 23:46:24,652 Computation:
67
+ 2023-10-17 23:46:24,652 - compute on device: cuda:0
68
+ 2023-10-17 23:46:24,652 - embedding storage: none
69
+ 2023-10-17 23:46:24,652 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 23:46:24,652 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
71
+ 2023-10-17 23:46:24,652 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 23:46:24,652 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 23:46:24,652 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 23:46:31,930 epoch 1 - iter 147/1476 - loss 2.31899626 - time (sec): 7.28 - samples/sec: 2329.85 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 23:46:39,105 epoch 1 - iter 294/1476 - loss 1.45048025 - time (sec): 14.45 - samples/sec: 2365.81 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 23:46:47,005 epoch 1 - iter 441/1476 - loss 1.07259867 - time (sec): 22.35 - samples/sec: 2346.60 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 23:46:54,154 epoch 1 - iter 588/1476 - loss 0.88392950 - time (sec): 29.50 - samples/sec: 2345.91 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 23:47:01,280 epoch 1 - iter 735/1476 - loss 0.76313219 - time (sec): 36.63 - samples/sec: 2335.02 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 23:47:08,128 epoch 1 - iter 882/1476 - loss 0.67915084 - time (sec): 43.48 - samples/sec: 2311.84 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 23:47:15,216 epoch 1 - iter 1029/1476 - loss 0.61481908 - time (sec): 50.56 - samples/sec: 2290.47 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 23:47:22,755 epoch 1 - iter 1176/1476 - loss 0.55954865 - time (sec): 58.10 - samples/sec: 2319.20 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 23:47:29,643 epoch 1 - iter 1323/1476 - loss 0.52079959 - time (sec): 64.99 - samples/sec: 2305.27 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 23:47:36,760 epoch 1 - iter 1470/1476 - loss 0.48589065 - time (sec): 72.11 - samples/sec: 2296.69 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 23:47:37,047 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 23:47:37,047 EPOCH 1 done: loss 0.4841 - lr: 0.000050
86
+ 2023-10-17 23:47:43,227 DEV : loss 0.21548223495483398 - f1-score (micro avg) 0.711
87
+ 2023-10-17 23:47:43,257 saving best model
88
+ 2023-10-17 23:47:43,646 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 23:47:51,091 epoch 2 - iter 147/1476 - loss 0.16619350 - time (sec): 7.44 - samples/sec: 2288.68 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 23:47:58,312 epoch 2 - iter 294/1476 - loss 0.15471014 - time (sec): 14.66 - samples/sec: 2261.06 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 23:48:05,399 epoch 2 - iter 441/1476 - loss 0.14876748 - time (sec): 21.75 - samples/sec: 2282.38 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 23:48:12,345 epoch 2 - iter 588/1476 - loss 0.14471294 - time (sec): 28.70 - samples/sec: 2289.61 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 23:48:19,229 epoch 2 - iter 735/1476 - loss 0.14973764 - time (sec): 35.58 - samples/sec: 2273.89 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 23:48:26,217 epoch 2 - iter 882/1476 - loss 0.14410801 - time (sec): 42.57 - samples/sec: 2298.46 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 23:48:33,474 epoch 2 - iter 1029/1476 - loss 0.14102429 - time (sec): 49.83 - samples/sec: 2307.16 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 23:48:41,170 epoch 2 - iter 1176/1476 - loss 0.13898171 - time (sec): 57.52 - samples/sec: 2336.77 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 23:48:48,266 epoch 2 - iter 1323/1476 - loss 0.13989011 - time (sec): 64.62 - samples/sec: 2330.81 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 23:48:55,244 epoch 2 - iter 1470/1476 - loss 0.14015703 - time (sec): 71.60 - samples/sec: 2317.38 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 23:48:55,511 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 23:48:55,512 EPOCH 2 done: loss 0.1399 - lr: 0.000044
101
+ 2023-10-17 23:49:07,371 DEV : loss 0.14165526628494263 - f1-score (micro avg) 0.7864
102
+ 2023-10-17 23:49:07,403 saving best model
103
+ 2023-10-17 23:49:07,920 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 23:49:15,672 epoch 3 - iter 147/1476 - loss 0.07240309 - time (sec): 7.75 - samples/sec: 2092.81 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 23:49:22,806 epoch 3 - iter 294/1476 - loss 0.07477988 - time (sec): 14.88 - samples/sec: 2162.41 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 23:49:30,056 epoch 3 - iter 441/1476 - loss 0.08692481 - time (sec): 22.13 - samples/sec: 2209.79 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 23:49:37,169 epoch 3 - iter 588/1476 - loss 0.09465275 - time (sec): 29.25 - samples/sec: 2210.62 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 23:49:44,545 epoch 3 - iter 735/1476 - loss 0.09240217 - time (sec): 36.62 - samples/sec: 2250.45 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 23:49:51,744 epoch 3 - iter 882/1476 - loss 0.09338741 - time (sec): 43.82 - samples/sec: 2241.95 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 23:49:59,135 epoch 3 - iter 1029/1476 - loss 0.09287578 - time (sec): 51.21 - samples/sec: 2272.20 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 23:50:06,210 epoch 3 - iter 1176/1476 - loss 0.09212955 - time (sec): 58.29 - samples/sec: 2271.37 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 23:50:13,318 epoch 3 - iter 1323/1476 - loss 0.09128009 - time (sec): 65.40 - samples/sec: 2274.94 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 23:50:20,611 epoch 3 - iter 1470/1476 - loss 0.09325358 - time (sec): 72.69 - samples/sec: 2282.28 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 23:50:20,877 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 23:50:20,877 EPOCH 3 done: loss 0.0934 - lr: 0.000039
116
+ 2023-10-17 23:50:32,390 DEV : loss 0.1794406771659851 - f1-score (micro avg) 0.7849
117
+ 2023-10-17 23:50:32,426 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 23:50:39,656 epoch 4 - iter 147/1476 - loss 0.04189508 - time (sec): 7.23 - samples/sec: 2373.29 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 23:50:46,610 epoch 4 - iter 294/1476 - loss 0.05999984 - time (sec): 14.18 - samples/sec: 2299.84 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 23:50:54,227 epoch 4 - iter 441/1476 - loss 0.06517904 - time (sec): 21.80 - samples/sec: 2341.18 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 23:51:01,702 epoch 4 - iter 588/1476 - loss 0.06966660 - time (sec): 29.27 - samples/sec: 2336.69 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 23:51:08,935 epoch 4 - iter 735/1476 - loss 0.06697795 - time (sec): 36.51 - samples/sec: 2292.75 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 23:51:16,058 epoch 4 - iter 882/1476 - loss 0.06639582 - time (sec): 43.63 - samples/sec: 2258.93 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 23:51:23,549 epoch 4 - iter 1029/1476 - loss 0.06530104 - time (sec): 51.12 - samples/sec: 2260.47 - lr: 0.000035 - momentum: 0.000000
125
+ 2023-10-17 23:51:30,834 epoch 4 - iter 1176/1476 - loss 0.06432796 - time (sec): 58.41 - samples/sec: 2266.96 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 23:51:38,572 epoch 4 - iter 1323/1476 - loss 0.06400953 - time (sec): 66.14 - samples/sec: 2237.08 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 23:51:47,005 epoch 4 - iter 1470/1476 - loss 0.06365817 - time (sec): 74.58 - samples/sec: 2224.59 - lr: 0.000033 - momentum: 0.000000
128
+ 2023-10-17 23:51:47,328 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 23:51:47,329 EPOCH 4 done: loss 0.0635 - lr: 0.000033
130
+ 2023-10-17 23:51:59,569 DEV : loss 0.1764398068189621 - f1-score (micro avg) 0.814
131
+ 2023-10-17 23:51:59,617 saving best model
132
+ 2023-10-17 23:52:00,200 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 23:52:07,564 epoch 5 - iter 147/1476 - loss 0.03148151 - time (sec): 7.36 - samples/sec: 2163.68 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 23:52:14,508 epoch 5 - iter 294/1476 - loss 0.03598276 - time (sec): 14.31 - samples/sec: 2220.63 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 23:52:21,489 epoch 5 - iter 441/1476 - loss 0.04162358 - time (sec): 21.29 - samples/sec: 2266.15 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 23:52:28,796 epoch 5 - iter 588/1476 - loss 0.04510912 - time (sec): 28.59 - samples/sec: 2280.82 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 23:52:35,875 epoch 5 - iter 735/1476 - loss 0.04497694 - time (sec): 35.67 - samples/sec: 2274.20 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 23:52:43,598 epoch 5 - iter 882/1476 - loss 0.04344617 - time (sec): 43.40 - samples/sec: 2329.01 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 23:52:50,968 epoch 5 - iter 1029/1476 - loss 0.04421788 - time (sec): 50.77 - samples/sec: 2336.93 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 23:52:58,041 epoch 5 - iter 1176/1476 - loss 0.04460316 - time (sec): 57.84 - samples/sec: 2314.04 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 23:53:04,814 epoch 5 - iter 1323/1476 - loss 0.04403883 - time (sec): 64.61 - samples/sec: 2289.09 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 23:53:12,210 epoch 5 - iter 1470/1476 - loss 0.04436491 - time (sec): 72.01 - samples/sec: 2304.02 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 23:53:12,479 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 23:53:12,479 EPOCH 5 done: loss 0.0442 - lr: 0.000028
145
+ 2023-10-17 23:53:24,386 DEV : loss 0.18140539526939392 - f1-score (micro avg) 0.8241
146
+ 2023-10-17 23:53:24,422 saving best model
147
+ 2023-10-17 23:53:25,011 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 23:53:32,585 epoch 6 - iter 147/1476 - loss 0.04187100 - time (sec): 7.57 - samples/sec: 2403.54 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 23:53:39,670 epoch 6 - iter 294/1476 - loss 0.03020420 - time (sec): 14.66 - samples/sec: 2352.90 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 23:53:47,148 epoch 6 - iter 441/1476 - loss 0.02675017 - time (sec): 22.14 - samples/sec: 2266.45 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 23:53:55,819 epoch 6 - iter 588/1476 - loss 0.02815533 - time (sec): 30.81 - samples/sec: 2278.66 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 23:54:02,951 epoch 6 - iter 735/1476 - loss 0.02827554 - time (sec): 37.94 - samples/sec: 2258.53 - lr: 0.000025 - momentum: 0.000000
153
+ 2023-10-17 23:54:10,133 epoch 6 - iter 882/1476 - loss 0.02887525 - time (sec): 45.12 - samples/sec: 2256.53 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 23:54:17,347 epoch 6 - iter 1029/1476 - loss 0.02838570 - time (sec): 52.33 - samples/sec: 2275.05 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 23:54:24,315 epoch 6 - iter 1176/1476 - loss 0.02791635 - time (sec): 59.30 - samples/sec: 2257.69 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 23:54:31,332 epoch 6 - iter 1323/1476 - loss 0.02743435 - time (sec): 66.32 - samples/sec: 2256.11 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 23:54:38,380 epoch 6 - iter 1470/1476 - loss 0.02754388 - time (sec): 73.37 - samples/sec: 2261.26 - lr: 0.000022 - momentum: 0.000000
158
+ 2023-10-17 23:54:38,648 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 23:54:38,648 EPOCH 6 done: loss 0.0275 - lr: 0.000022
160
+ 2023-10-17 23:54:50,572 DEV : loss 0.21165505051612854 - f1-score (micro avg) 0.8189
161
+ 2023-10-17 23:54:50,611 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-17 23:54:57,604 epoch 7 - iter 147/1476 - loss 0.03336044 - time (sec): 6.99 - samples/sec: 2202.23 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-17 23:55:04,867 epoch 7 - iter 294/1476 - loss 0.02830500 - time (sec): 14.25 - samples/sec: 2233.45 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 23:55:11,662 epoch 7 - iter 441/1476 - loss 0.02519746 - time (sec): 21.05 - samples/sec: 2242.77 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 23:55:18,747 epoch 7 - iter 588/1476 - loss 0.02427425 - time (sec): 28.13 - samples/sec: 2246.44 - lr: 0.000020 - momentum: 0.000000
166
+ 2023-10-17 23:55:26,660 epoch 7 - iter 735/1476 - loss 0.02353020 - time (sec): 36.05 - samples/sec: 2264.62 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 23:55:34,371 epoch 7 - iter 882/1476 - loss 0.02322784 - time (sec): 43.76 - samples/sec: 2205.99 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-17 23:55:41,845 epoch 7 - iter 1029/1476 - loss 0.02477380 - time (sec): 51.23 - samples/sec: 2214.26 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 23:55:49,162 epoch 7 - iter 1176/1476 - loss 0.02374289 - time (sec): 58.55 - samples/sec: 2238.37 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 23:55:56,331 epoch 7 - iter 1323/1476 - loss 0.02328721 - time (sec): 65.72 - samples/sec: 2249.63 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 23:56:03,765 epoch 7 - iter 1470/1476 - loss 0.02252800 - time (sec): 73.15 - samples/sec: 2264.17 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 23:56:04,039 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-17 23:56:04,039 EPOCH 7 done: loss 0.0225 - lr: 0.000017
174
+ 2023-10-17 23:56:15,766 DEV : loss 0.22102110087871552 - f1-score (micro avg) 0.8288
175
+ 2023-10-17 23:56:15,801 saving best model
176
+ 2023-10-17 23:56:16,352 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 23:56:23,364 epoch 8 - iter 147/1476 - loss 0.01157989 - time (sec): 7.01 - samples/sec: 2322.40 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 23:56:30,121 epoch 8 - iter 294/1476 - loss 0.01167708 - time (sec): 13.77 - samples/sec: 2240.73 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 23:56:37,509 epoch 8 - iter 441/1476 - loss 0.00968561 - time (sec): 21.16 - samples/sec: 2317.22 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-17 23:56:44,454 epoch 8 - iter 588/1476 - loss 0.00985733 - time (sec): 28.10 - samples/sec: 2278.99 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 23:56:51,836 epoch 8 - iter 735/1476 - loss 0.01133488 - time (sec): 35.48 - samples/sec: 2325.78 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 23:56:59,035 epoch 8 - iter 882/1476 - loss 0.01248439 - time (sec): 42.68 - samples/sec: 2316.77 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 23:57:06,073 epoch 8 - iter 1029/1476 - loss 0.01289164 - time (sec): 49.72 - samples/sec: 2299.82 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 23:57:12,782 epoch 8 - iter 1176/1476 - loss 0.01234089 - time (sec): 56.43 - samples/sec: 2296.02 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 23:57:20,061 epoch 8 - iter 1323/1476 - loss 0.01252386 - time (sec): 63.71 - samples/sec: 2282.19 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 23:57:27,897 epoch 8 - iter 1470/1476 - loss 0.01253658 - time (sec): 71.54 - samples/sec: 2315.07 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-17 23:57:28,179 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 23:57:28,180 EPOCH 8 done: loss 0.0125 - lr: 0.000011
189
+ 2023-10-17 23:57:39,811 DEV : loss 0.21121571958065033 - f1-score (micro avg) 0.8457
190
+ 2023-10-17 23:57:39,845 saving best model
191
+ 2023-10-17 23:57:40,402 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-17 23:57:47,741 epoch 9 - iter 147/1476 - loss 0.00964780 - time (sec): 7.34 - samples/sec: 2199.97 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-17 23:57:54,762 epoch 9 - iter 294/1476 - loss 0.00914997 - time (sec): 14.36 - samples/sec: 2240.19 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-17 23:58:02,050 epoch 9 - iter 441/1476 - loss 0.00923034 - time (sec): 21.65 - samples/sec: 2313.28 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-17 23:58:08,743 epoch 9 - iter 588/1476 - loss 0.00767134 - time (sec): 28.34 - samples/sec: 2324.21 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 23:58:15,646 epoch 9 - iter 735/1476 - loss 0.00728748 - time (sec): 35.24 - samples/sec: 2370.99 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 23:58:22,401 epoch 9 - iter 882/1476 - loss 0.00929956 - time (sec): 42.00 - samples/sec: 2362.21 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 23:58:29,273 epoch 9 - iter 1029/1476 - loss 0.00884665 - time (sec): 48.87 - samples/sec: 2346.38 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 23:58:36,688 epoch 9 - iter 1176/1476 - loss 0.00813902 - time (sec): 56.28 - samples/sec: 2351.01 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 23:58:43,773 epoch 9 - iter 1323/1476 - loss 0.00784879 - time (sec): 63.37 - samples/sec: 2344.88 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 23:58:50,973 epoch 9 - iter 1470/1476 - loss 0.00820699 - time (sec): 70.57 - samples/sec: 2340.07 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 23:58:51,378 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 23:58:51,379 EPOCH 9 done: loss 0.0082 - lr: 0.000006
204
+ 2023-10-17 23:59:02,756 DEV : loss 0.2453046441078186 - f1-score (micro avg) 0.8427
205
+ 2023-10-17 23:59:02,789 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-17 23:59:10,200 epoch 10 - iter 147/1476 - loss 0.00176823 - time (sec): 7.41 - samples/sec: 2383.35 - lr: 0.000005 - momentum: 0.000000
207
+ 2023-10-17 23:59:17,026 epoch 10 - iter 294/1476 - loss 0.00524086 - time (sec): 14.24 - samples/sec: 2414.74 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 23:59:23,824 epoch 10 - iter 441/1476 - loss 0.00516859 - time (sec): 21.03 - samples/sec: 2405.97 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-17 23:59:31,060 epoch 10 - iter 588/1476 - loss 0.00530312 - time (sec): 28.27 - samples/sec: 2434.57 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 23:59:38,111 epoch 10 - iter 735/1476 - loss 0.00452613 - time (sec): 35.32 - samples/sec: 2403.30 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 23:59:45,220 epoch 10 - iter 882/1476 - loss 0.00426851 - time (sec): 42.43 - samples/sec: 2392.74 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 23:59:52,215 epoch 10 - iter 1029/1476 - loss 0.00407151 - time (sec): 49.42 - samples/sec: 2365.78 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 23:59:59,493 epoch 10 - iter 1176/1476 - loss 0.00383502 - time (sec): 56.70 - samples/sec: 2341.96 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-18 00:00:06,798 epoch 10 - iter 1323/1476 - loss 0.00389736 - time (sec): 64.01 - samples/sec: 2331.27 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-18 00:00:13,976 epoch 10 - iter 1470/1476 - loss 0.00414410 - time (sec): 71.19 - samples/sec: 2329.56 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-18 00:00:14,268 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-18 00:00:14,268 EPOCH 10 done: loss 0.0042 - lr: 0.000000
218
+ 2023-10-18 00:00:26,564 DEV : loss 0.2395576387643814 - f1-score (micro avg) 0.8488
219
+ 2023-10-18 00:00:26,608 saving best model
220
+ 2023-10-18 00:00:27,721 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-18 00:00:27,723 Loading model from best epoch ...
222
+ 2023-10-18 00:00:29,126 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
+ 2023-10-18 00:00:36,049
224
+ Results:
225
+ - F-score (micro) 0.8138
226
+ - F-score (macro) 0.7187
227
+ - Accuracy 0.7058
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.8806 0.8858 0.8832 858
233
+ pers 0.7688 0.7989 0.7836 537
234
+ org 0.6385 0.6288 0.6336 132
235
+ prod 0.7018 0.6557 0.6780 61
236
+ time 0.5714 0.6667 0.6154 54
237
+
238
+ micro avg 0.8067 0.8210 0.8138 1642
239
+ macro avg 0.7122 0.7272 0.7187 1642
240
+ weighted avg 0.8078 0.8210 0.8141 1642
241
+
242
+ 2023-10-18 00:00:36,049 ----------------------------------------------------------------------------------------------------