Hugging Face's logo

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

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
681670f
•
1 Parent(s): a65b836

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.1697574037.bce904bcef33.2482.3 +3 -0
  5. test.tsv +0 -0
  6. training.log +241 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb25fd66035d55bf69acc7a8d1bb0ccc27e2642f05e11a7181cbc0707011152
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 20:21:56 0.0000 0.5008 0.1227 0.7281 0.7824 0.7543 0.6283
3
+ 2 20:23:21 0.0000 0.1411 0.1605 0.6662 0.7417 0.7019 0.5700
4
+ 3 20:24:46 0.0000 0.0932 0.1321 0.7669 0.8310 0.7977 0.6803
5
+ 4 20:26:11 0.0000 0.0681 0.1755 0.8191 0.8351 0.8270 0.7319
6
+ 5 20:27:37 0.0000 0.0476 0.2104 0.8457 0.8162 0.8307 0.7330
7
+ 6 20:29:01 0.0000 0.0332 0.1892 0.8243 0.8328 0.8285 0.7259
8
+ 7 20:30:29 0.0000 0.0222 0.2224 0.8411 0.8339 0.8375 0.7455
9
+ 8 20:31:55 0.0000 0.0147 0.2161 0.8424 0.8356 0.8390 0.7494
10
+ 9 20:33:28 0.0000 0.0081 0.2256 0.8393 0.8345 0.8369 0.7449
11
+ 10 20:34:59 0.0000 0.0061 0.2356 0.8332 0.8356 0.8344 0.7406
runs/events.out.tfevents.1697574037.bce904bcef33.2482.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5e8505b34f84debbab47d4233055398fb5c1f54d3de92af5f3ff85758ae75e
3
+ size 825716
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 20:20:37,487 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 20:20:37,488 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 20:20:37,488 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 20:20:37,488 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 20:20:37,488 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 20:20:37,488 Train: 5901 sentences
51
+ 2023-10-17 20:20:37,488 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 20:20:37,488 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 20:20:37,488 Training Params:
54
+ 2023-10-17 20:20:37,488 - learning_rate: "5e-05"
55
+ 2023-10-17 20:20:37,489 - mini_batch_size: "4"
56
+ 2023-10-17 20:20:37,489 - max_epochs: "10"
57
+ 2023-10-17 20:20:37,489 - shuffle: "True"
58
+ 2023-10-17 20:20:37,489 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 20:20:37,489 Plugins:
60
+ 2023-10-17 20:20:37,489 - TensorboardLogger
61
+ 2023-10-17 20:20:37,489 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 20:20:37,489 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 20:20:37,489 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 20:20:37,489 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 20:20:37,489 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 20:20:37,489 Computation:
67
+ 2023-10-17 20:20:37,489 - compute on device: cuda:0
68
+ 2023-10-17 20:20:37,489 - embedding storage: none
69
+ 2023-10-17 20:20:37,489 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 20:20:37,489 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
71
+ 2023-10-17 20:20:37,489 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 20:20:37,489 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 20:20:37,489 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 20:20:45,045 epoch 1 - iter 147/1476 - loss 2.45075682 - time (sec): 7.55 - samples/sec: 2345.15 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 20:20:52,026 epoch 1 - iter 294/1476 - loss 1.54365509 - time (sec): 14.54 - samples/sec: 2280.56 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 20:20:59,562 epoch 1 - iter 441/1476 - loss 1.13854388 - time (sec): 22.07 - samples/sec: 2333.15 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 20:21:06,932 epoch 1 - iter 588/1476 - loss 0.91730690 - time (sec): 29.44 - samples/sec: 2358.65 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 20:21:14,098 epoch 1 - iter 735/1476 - loss 0.78832461 - time (sec): 36.61 - samples/sec: 2336.33 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 20:21:21,137 epoch 1 - iter 882/1476 - loss 0.70576861 - time (sec): 43.65 - samples/sec: 2298.06 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 20:21:28,234 epoch 1 - iter 1029/1476 - loss 0.64071654 - time (sec): 50.74 - samples/sec: 2286.04 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 20:21:35,283 epoch 1 - iter 1176/1476 - loss 0.58480153 - time (sec): 57.79 - samples/sec: 2286.47 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 20:21:42,496 epoch 1 - iter 1323/1476 - loss 0.54130591 - time (sec): 65.01 - samples/sec: 2285.85 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 20:21:49,635 epoch 1 - iter 1470/1476 - loss 0.50188471 - time (sec): 72.14 - samples/sec: 2299.29 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 20:21:49,886 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 20:21:49,886 EPOCH 1 done: loss 0.5008 - lr: 0.000050
86
+ 2023-10-17 20:21:56,210 DEV : loss 0.12269438803195953 - f1-score (micro avg) 0.7543
87
+ 2023-10-17 20:21:56,243 saving best model
88
+ 2023-10-17 20:21:56,600 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 20:22:03,964 epoch 2 - iter 147/1476 - loss 0.15141280 - time (sec): 7.36 - samples/sec: 2270.51 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 20:22:11,323 epoch 2 - iter 294/1476 - loss 0.15112657 - time (sec): 14.72 - samples/sec: 2373.19 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 20:22:18,876 epoch 2 - iter 441/1476 - loss 0.14768430 - time (sec): 22.27 - samples/sec: 2351.50 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 20:22:25,980 epoch 2 - iter 588/1476 - loss 0.14500357 - time (sec): 29.38 - samples/sec: 2312.57 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 20:22:33,091 epoch 2 - iter 735/1476 - loss 0.14249498 - time (sec): 36.49 - samples/sec: 2254.48 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 20:22:40,077 epoch 2 - iter 882/1476 - loss 0.14525703 - time (sec): 43.48 - samples/sec: 2246.59 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 20:22:47,573 epoch 2 - iter 1029/1476 - loss 0.14238917 - time (sec): 50.97 - samples/sec: 2239.06 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 20:22:54,845 epoch 2 - iter 1176/1476 - loss 0.14182713 - time (sec): 58.24 - samples/sec: 2239.66 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 20:23:02,268 epoch 2 - iter 1323/1476 - loss 0.14190065 - time (sec): 65.67 - samples/sec: 2261.46 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 20:23:09,457 epoch 2 - iter 1470/1476 - loss 0.14112657 - time (sec): 72.86 - samples/sec: 2276.21 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 20:23:09,710 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 20:23:09,710 EPOCH 2 done: loss 0.1411 - lr: 0.000044
101
+ 2023-10-17 20:23:21,174 DEV : loss 0.16049356758594513 - f1-score (micro avg) 0.7019
102
+ 2023-10-17 20:23:21,207 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-17 20:23:28,726 epoch 3 - iter 147/1476 - loss 0.08022691 - time (sec): 7.52 - samples/sec: 2350.39 - lr: 0.000044 - momentum: 0.000000
104
+ 2023-10-17 20:23:36,021 epoch 3 - iter 294/1476 - loss 0.08406285 - time (sec): 14.81 - samples/sec: 2373.14 - lr: 0.000043 - momentum: 0.000000
105
+ 2023-10-17 20:23:43,025 epoch 3 - iter 441/1476 - loss 0.08796088 - time (sec): 21.82 - samples/sec: 2379.86 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 20:23:50,369 epoch 3 - iter 588/1476 - loss 0.09119106 - time (sec): 29.16 - samples/sec: 2330.63 - lr: 0.000042 - momentum: 0.000000
107
+ 2023-10-17 20:23:57,561 epoch 3 - iter 735/1476 - loss 0.09523907 - time (sec): 36.35 - samples/sec: 2322.17 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 20:24:04,678 epoch 3 - iter 882/1476 - loss 0.09396738 - time (sec): 43.47 - samples/sec: 2293.44 - lr: 0.000041 - momentum: 0.000000
109
+ 2023-10-17 20:24:12,835 epoch 3 - iter 1029/1476 - loss 0.09373264 - time (sec): 51.63 - samples/sec: 2278.70 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 20:24:20,129 epoch 3 - iter 1176/1476 - loss 0.09469625 - time (sec): 58.92 - samples/sec: 2270.69 - lr: 0.000040 - momentum: 0.000000
111
+ 2023-10-17 20:24:27,320 epoch 3 - iter 1323/1476 - loss 0.09368396 - time (sec): 66.11 - samples/sec: 2267.77 - lr: 0.000039 - momentum: 0.000000
112
+ 2023-10-17 20:24:34,665 epoch 3 - iter 1470/1476 - loss 0.09312445 - time (sec): 73.46 - samples/sec: 2259.50 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 20:24:34,937 ----------------------------------------------------------------------------------------------------
114
+ 2023-10-17 20:24:34,938 EPOCH 3 done: loss 0.0932 - lr: 0.000039
115
+ 2023-10-17 20:24:46,497 DEV : loss 0.13214744627475739 - f1-score (micro avg) 0.7977
116
+ 2023-10-17 20:24:46,530 saving best model
117
+ 2023-10-17 20:24:47,001 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 20:24:54,116 epoch 4 - iter 147/1476 - loss 0.07305392 - time (sec): 7.11 - samples/sec: 2239.81 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 20:25:01,367 epoch 4 - iter 294/1476 - loss 0.06289770 - time (sec): 14.36 - samples/sec: 2348.53 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 20:25:08,480 epoch 4 - iter 441/1476 - loss 0.06776105 - time (sec): 21.48 - samples/sec: 2284.26 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 20:25:16,121 epoch 4 - iter 588/1476 - loss 0.06873963 - time (sec): 29.12 - samples/sec: 2252.25 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 20:25:23,375 epoch 4 - iter 735/1476 - loss 0.07185754 - time (sec): 36.37 - samples/sec: 2207.32 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 20:25:30,807 epoch 4 - iter 882/1476 - loss 0.06900936 - time (sec): 43.80 - samples/sec: 2216.41 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 20:25:37,796 epoch 4 - iter 1029/1476 - loss 0.06636325 - time (sec): 50.79 - samples/sec: 2221.93 - lr: 0.000035 - momentum: 0.000000
125
+ 2023-10-17 20:25:45,174 epoch 4 - iter 1176/1476 - loss 0.06586245 - time (sec): 58.17 - samples/sec: 2252.10 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 20:25:52,240 epoch 4 - iter 1323/1476 - loss 0.06697787 - time (sec): 65.24 - samples/sec: 2255.01 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 20:25:59,983 epoch 4 - iter 1470/1476 - loss 0.06808951 - time (sec): 72.98 - samples/sec: 2271.08 - lr: 0.000033 - momentum: 0.000000
128
+ 2023-10-17 20:26:00,291 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 20:26:00,292 EPOCH 4 done: loss 0.0681 - lr: 0.000033
130
+ 2023-10-17 20:26:11,758 DEV : loss 0.1754840463399887 - f1-score (micro avg) 0.827
131
+ 2023-10-17 20:26:11,791 saving best model
132
+ 2023-10-17 20:26:12,273 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 20:26:19,589 epoch 5 - iter 147/1476 - loss 0.04825016 - time (sec): 7.31 - samples/sec: 2436.31 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 20:26:26,872 epoch 5 - iter 294/1476 - loss 0.04930976 - time (sec): 14.59 - samples/sec: 2309.14 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 20:26:34,166 epoch 5 - iter 441/1476 - loss 0.04770019 - time (sec): 21.89 - samples/sec: 2307.01 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 20:26:41,138 epoch 5 - iter 588/1476 - loss 0.04688871 - time (sec): 28.86 - samples/sec: 2317.40 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 20:26:48,383 epoch 5 - iter 735/1476 - loss 0.04601401 - time (sec): 36.10 - samples/sec: 2323.11 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 20:26:55,592 epoch 5 - iter 882/1476 - loss 0.04384687 - time (sec): 43.31 - samples/sec: 2318.19 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 20:27:03,155 epoch 5 - iter 1029/1476 - loss 0.04285307 - time (sec): 50.87 - samples/sec: 2285.79 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 20:27:10,270 epoch 5 - iter 1176/1476 - loss 0.04658069 - time (sec): 57.99 - samples/sec: 2269.90 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 20:27:17,743 epoch 5 - iter 1323/1476 - loss 0.04712647 - time (sec): 65.46 - samples/sec: 2293.93 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 20:27:25,424 epoch 5 - iter 1470/1476 - loss 0.04713805 - time (sec): 73.14 - samples/sec: 2268.84 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 20:27:25,686 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 20:27:25,686 EPOCH 5 done: loss 0.0476 - lr: 0.000028
145
+ 2023-10-17 20:27:37,323 DEV : loss 0.21042108535766602 - f1-score (micro avg) 0.8307
146
+ 2023-10-17 20:27:37,354 saving best model
147
+ 2023-10-17 20:27:37,817 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 20:27:44,810 epoch 6 - iter 147/1476 - loss 0.03453912 - time (sec): 6.99 - samples/sec: 2265.05 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 20:27:51,917 epoch 6 - iter 294/1476 - loss 0.03647166 - time (sec): 14.10 - samples/sec: 2343.34 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 20:27:58,988 epoch 6 - iter 441/1476 - loss 0.03049749 - time (sec): 21.17 - samples/sec: 2351.10 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 20:28:06,214 epoch 6 - iter 588/1476 - loss 0.03256111 - time (sec): 28.39 - samples/sec: 2317.20 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 20:28:13,245 epoch 6 - iter 735/1476 - loss 0.03378667 - time (sec): 35.42 - samples/sec: 2312.00 - lr: 0.000025 - momentum: 0.000000
153
+ 2023-10-17 20:28:20,160 epoch 6 - iter 882/1476 - loss 0.03314087 - time (sec): 42.34 - samples/sec: 2304.81 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 20:28:27,651 epoch 6 - iter 1029/1476 - loss 0.03089634 - time (sec): 49.83 - samples/sec: 2307.34 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 20:28:34,770 epoch 6 - iter 1176/1476 - loss 0.03003096 - time (sec): 56.95 - samples/sec: 2309.76 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 20:28:41,901 epoch 6 - iter 1323/1476 - loss 0.03187601 - time (sec): 64.08 - samples/sec: 2305.63 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 20:28:49,320 epoch 6 - iter 1470/1476 - loss 0.03330083 - time (sec): 71.50 - samples/sec: 2319.18 - lr: 0.000022 - momentum: 0.000000
158
+ 2023-10-17 20:28:49,614 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 20:28:49,614 EPOCH 6 done: loss 0.0332 - lr: 0.000022
160
+ 2023-10-17 20:29:01,261 DEV : loss 0.18915601074695587 - f1-score (micro avg) 0.8285
161
+ 2023-10-17 20:29:01,298 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-17 20:29:08,867 epoch 7 - iter 147/1476 - loss 0.01653898 - time (sec): 7.57 - samples/sec: 2231.80 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-17 20:29:17,104 epoch 7 - iter 294/1476 - loss 0.02599015 - time (sec): 15.80 - samples/sec: 2102.79 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 20:29:24,982 epoch 7 - iter 441/1476 - loss 0.02861579 - time (sec): 23.68 - samples/sec: 2159.44 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 20:29:32,237 epoch 7 - iter 588/1476 - loss 0.02528070 - time (sec): 30.94 - samples/sec: 2219.64 - lr: 0.000020 - momentum: 0.000000
166
+ 2023-10-17 20:29:39,342 epoch 7 - iter 735/1476 - loss 0.02570093 - time (sec): 38.04 - samples/sec: 2218.06 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 20:29:46,643 epoch 7 - iter 882/1476 - loss 0.02442225 - time (sec): 45.34 - samples/sec: 2231.31 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-17 20:29:53,635 epoch 7 - iter 1029/1476 - loss 0.02453850 - time (sec): 52.34 - samples/sec: 2235.33 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 20:30:01,791 epoch 7 - iter 1176/1476 - loss 0.02386131 - time (sec): 60.49 - samples/sec: 2217.70 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 20:30:09,880 epoch 7 - iter 1323/1476 - loss 0.02311452 - time (sec): 68.58 - samples/sec: 2204.29 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 20:30:17,172 epoch 7 - iter 1470/1476 - loss 0.02213326 - time (sec): 75.87 - samples/sec: 2186.09 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 20:30:17,451 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-17 20:30:17,451 EPOCH 7 done: loss 0.0222 - lr: 0.000017
174
+ 2023-10-17 20:30:29,432 DEV : loss 0.22237005829811096 - f1-score (micro avg) 0.8375
175
+ 2023-10-17 20:30:29,467 saving best model
176
+ 2023-10-17 20:30:29,942 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 20:30:37,188 epoch 8 - iter 147/1476 - loss 0.00842618 - time (sec): 7.24 - samples/sec: 2253.24 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 20:30:44,981 epoch 8 - iter 294/1476 - loss 0.00786122 - time (sec): 15.04 - samples/sec: 2269.72 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 20:30:52,418 epoch 8 - iter 441/1476 - loss 0.01083371 - time (sec): 22.47 - samples/sec: 2214.32 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-17 20:30:59,408 epoch 8 - iter 588/1476 - loss 0.01158928 - time (sec): 29.46 - samples/sec: 2230.67 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 20:31:06,510 epoch 8 - iter 735/1476 - loss 0.01381677 - time (sec): 36.57 - samples/sec: 2262.93 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 20:31:13,291 epoch 8 - iter 882/1476 - loss 0.01326944 - time (sec): 43.35 - samples/sec: 2266.51 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 20:31:21,217 epoch 8 - iter 1029/1476 - loss 0.01584565 - time (sec): 51.27 - samples/sec: 2295.28 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 20:31:28,174 epoch 8 - iter 1176/1476 - loss 0.01500981 - time (sec): 58.23 - samples/sec: 2292.30 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 20:31:35,385 epoch 8 - iter 1323/1476 - loss 0.01457328 - time (sec): 65.44 - samples/sec: 2296.33 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 20:31:42,554 epoch 8 - iter 1470/1476 - loss 0.01473348 - time (sec): 72.61 - samples/sec: 2278.84 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-17 20:31:42,937 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 20:31:42,937 EPOCH 8 done: loss 0.0147 - lr: 0.000011
189
+ 2023-10-17 20:31:55,009 DEV : loss 0.2160811871290207 - f1-score (micro avg) 0.839
190
+ 2023-10-17 20:31:55,060 saving best model
191
+ 2023-10-17 20:31:55,642 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-17 20:32:04,050 epoch 9 - iter 147/1476 - loss 0.00655270 - time (sec): 8.41 - samples/sec: 2143.44 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-17 20:32:12,106 epoch 9 - iter 294/1476 - loss 0.00851486 - time (sec): 16.46 - samples/sec: 2211.15 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-17 20:32:20,382 epoch 9 - iter 441/1476 - loss 0.00841270 - time (sec): 24.74 - samples/sec: 2210.55 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-17 20:32:28,491 epoch 9 - iter 588/1476 - loss 0.00821208 - time (sec): 32.85 - samples/sec: 2128.04 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 20:32:36,654 epoch 9 - iter 735/1476 - loss 0.00783197 - time (sec): 41.01 - samples/sec: 2096.88 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 20:32:44,502 epoch 9 - iter 882/1476 - loss 0.00844606 - time (sec): 48.86 - samples/sec: 2093.27 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 20:32:52,126 epoch 9 - iter 1029/1476 - loss 0.00913720 - time (sec): 56.48 - samples/sec: 2077.93 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 20:32:59,984 epoch 9 - iter 1176/1476 - loss 0.00836341 - time (sec): 64.34 - samples/sec: 2065.61 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 20:33:08,375 epoch 9 - iter 1323/1476 - loss 0.00807285 - time (sec): 72.73 - samples/sec: 2079.22 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 20:33:15,939 epoch 9 - iter 1470/1476 - loss 0.00815447 - time (sec): 80.30 - samples/sec: 2063.52 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 20:33:16,264 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 20:33:16,264 EPOCH 9 done: loss 0.0081 - lr: 0.000006
204
+ 2023-10-17 20:33:28,004 DEV : loss 0.22555013000965118 - f1-score (micro avg) 0.8369
205
+ 2023-10-17 20:33:28,043 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-17 20:33:36,574 epoch 10 - iter 147/1476 - loss 0.00592010 - time (sec): 8.53 - samples/sec: 2314.54 - lr: 0.000005 - momentum: 0.000000
207
+ 2023-10-17 20:33:45,359 epoch 10 - iter 294/1476 - loss 0.00415630 - time (sec): 17.31 - samples/sec: 2137.17 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 20:33:53,166 epoch 10 - iter 441/1476 - loss 0.00430526 - time (sec): 25.12 - samples/sec: 2120.30 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-17 20:34:00,904 epoch 10 - iter 588/1476 - loss 0.00403158 - time (sec): 32.86 - samples/sec: 2070.07 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 20:34:08,706 epoch 10 - iter 735/1476 - loss 0.00450434 - time (sec): 40.66 - samples/sec: 2059.10 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 20:34:16,327 epoch 10 - iter 882/1476 - loss 0.00429572 - time (sec): 48.28 - samples/sec: 2066.70 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 20:34:24,451 epoch 10 - iter 1029/1476 - loss 0.00479129 - time (sec): 56.41 - samples/sec: 2075.91 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 20:34:32,203 epoch 10 - iter 1176/1476 - loss 0.00542076 - time (sec): 64.16 - samples/sec: 2065.92 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 20:34:39,990 epoch 10 - iter 1323/1476 - loss 0.00558378 - time (sec): 71.95 - samples/sec: 2061.86 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 20:34:47,979 epoch 10 - iter 1470/1476 - loss 0.00606797 - time (sec): 79.93 - samples/sec: 2075.49 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-17 20:34:48,280 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-17 20:34:48,280 EPOCH 10 done: loss 0.0061 - lr: 0.000000
218
+ 2023-10-17 20:34:59,857 DEV : loss 0.2355625480413437 - f1-score (micro avg) 0.8344
219
+ 2023-10-17 20:35:00,410 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-17 20:35:00,411 Loading model from best epoch ...
221
+ 2023-10-17 20:35:02,129 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
222
+ 2023-10-17 20:35:08,299
223
+ Results:
224
+ - F-score (micro) 0.8028
225
+ - F-score (macro) 0.7089
226
+ - Accuracy 0.691
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ loc 0.8573 0.8683 0.8628 858
232
+ pers 0.7960 0.8063 0.8011 537
233
+ org 0.5260 0.6136 0.5664 132
234
+ prod 0.7167 0.7049 0.7107 61
235
+ time 0.5645 0.6481 0.6034 54
236
+
237
+ micro avg 0.7916 0.8143 0.8028 1642
238
+ macro avg 0.6921 0.7283 0.7089 1642
239
+ weighted avg 0.7958 0.8143 0.8046 1642
240
+
241
+ 2023-10-17 20:35:08,299 ----------------------------------------------------------------------------------------------------