Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmteams-bs4-wsFalse-e10-lr3e-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
8277da3
•
1 Parent(s): 2524b44

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.1697585514.bce904bcef33.2482.18 +3 -0
  5. test.tsv +0 -0
  6. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d02398f15dddba313c2da936c3a9a3755c0bffc4d324df393c5fb4b6921755
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 23:33:11 0.0000 0.5696 0.1295 0.7804 0.7858 0.7831 0.6606
3
+ 2 23:34:35 0.0000 0.1282 0.1176 0.7704 0.8419 0.8046 0.6918
4
+ 3 23:35:59 0.0000 0.0845 0.1246 0.8146 0.8482 0.8311 0.7361
5
+ 4 23:37:24 0.0000 0.0589 0.1730 0.8111 0.8631 0.8363 0.7416
6
+ 5 23:38:49 0.0000 0.0396 0.1907 0.8106 0.8603 0.8347 0.7363
7
+ 6 23:40:12 0.0000 0.0276 0.2225 0.8013 0.8454 0.8227 0.7311
8
+ 7 23:41:34 0.0000 0.0190 0.2077 0.8289 0.8574 0.8429 0.7481
9
+ 8 23:42:58 0.0000 0.0156 0.1886 0.8531 0.8545 0.8538 0.7659
10
+ 9 23:44:22 0.0000 0.0089 0.2055 0.8534 0.8637 0.8585 0.7718
11
+ 10 23:45:46 0.0000 0.0064 0.2084 0.8588 0.8603 0.8595 0.7734
runs/events.out.tfevents.1697585514.bce904bcef33.2482.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266910cf8c0080ad3c2efab822de33758e0fe16c74bc95c1f3711cf3169666cb
3
+ size 825716
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 23:31:54,079 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 23:31:54,080 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 23:31:54,080 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 23:31:54,080 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 23:31:54,080 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 23:31:54,081 Train: 5901 sentences
51
+ 2023-10-17 23:31:54,081 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 23:31:54,081 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 23:31:54,081 Training Params:
54
+ 2023-10-17 23:31:54,081 - learning_rate: "3e-05"
55
+ 2023-10-17 23:31:54,081 - mini_batch_size: "4"
56
+ 2023-10-17 23:31:54,081 - max_epochs: "10"
57
+ 2023-10-17 23:31:54,081 - shuffle: "True"
58
+ 2023-10-17 23:31:54,081 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 23:31:54,081 Plugins:
60
+ 2023-10-17 23:31:54,081 - TensorboardLogger
61
+ 2023-10-17 23:31:54,081 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 23:31:54,081 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 23:31:54,081 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 23:31:54,081 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 23:31:54,081 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 23:31:54,081 Computation:
67
+ 2023-10-17 23:31:54,081 - compute on device: cuda:0
68
+ 2023-10-17 23:31:54,081 - embedding storage: none
69
+ 2023-10-17 23:31:54,081 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 23:31:54,081 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
71
+ 2023-10-17 23:31:54,081 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 23:31:54,081 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 23:31:54,081 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 23:32:01,352 epoch 1 - iter 147/1476 - loss 2.80100325 - time (sec): 7.27 - samples/sec: 2332.20 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 23:32:08,598 epoch 1 - iter 294/1476 - loss 1.73992832 - time (sec): 14.52 - samples/sec: 2355.51 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 23:32:16,120 epoch 1 - iter 441/1476 - loss 1.28272528 - time (sec): 22.04 - samples/sec: 2380.08 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 23:32:23,324 epoch 1 - iter 588/1476 - loss 1.05514826 - time (sec): 29.24 - samples/sec: 2366.74 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 23:32:30,350 epoch 1 - iter 735/1476 - loss 0.91050463 - time (sec): 36.27 - samples/sec: 2358.18 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 23:32:37,153 epoch 1 - iter 882/1476 - loss 0.81059549 - time (sec): 43.07 - samples/sec: 2333.54 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 23:32:43,975 epoch 1 - iter 1029/1476 - loss 0.73282939 - time (sec): 49.89 - samples/sec: 2321.26 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 23:32:51,442 epoch 1 - iter 1176/1476 - loss 0.66324521 - time (sec): 57.36 - samples/sec: 2349.23 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 23:32:58,230 epoch 1 - iter 1323/1476 - loss 0.61491813 - time (sec): 64.15 - samples/sec: 2335.55 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 23:33:05,023 epoch 1 - iter 1470/1476 - loss 0.57169143 - time (sec): 70.94 - samples/sec: 2334.46 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 23:33:05,308 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 23:33:05,309 EPOCH 1 done: loss 0.5696 - lr: 0.000030
86
+ 2023-10-17 23:33:11,826 DEV : loss 0.1295262575149536 - f1-score (micro avg) 0.7831
87
+ 2023-10-17 23:33:11,862 saving best model
88
+ 2023-10-17 23:33:12,267 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 23:33:19,808 epoch 2 - iter 147/1476 - loss 0.14873257 - time (sec): 7.54 - samples/sec: 2259.44 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 23:33:27,056 epoch 2 - iter 294/1476 - loss 0.13554378 - time (sec): 14.79 - samples/sec: 2242.31 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 23:33:33,971 epoch 2 - iter 441/1476 - loss 0.13082620 - time (sec): 21.70 - samples/sec: 2287.60 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 23:33:41,017 epoch 2 - iter 588/1476 - loss 0.12999291 - time (sec): 28.75 - samples/sec: 2285.60 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 23:33:47,740 epoch 2 - iter 735/1476 - loss 0.13337666 - time (sec): 35.47 - samples/sec: 2280.96 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 23:33:54,755 epoch 2 - iter 882/1476 - loss 0.12980013 - time (sec): 42.49 - samples/sec: 2302.94 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 23:34:01,945 epoch 2 - iter 1029/1476 - loss 0.12828897 - time (sec): 49.68 - samples/sec: 2314.15 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 23:34:09,580 epoch 2 - iter 1176/1476 - loss 0.12736958 - time (sec): 57.31 - samples/sec: 2345.37 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 23:34:16,710 epoch 2 - iter 1323/1476 - loss 0.12756206 - time (sec): 64.44 - samples/sec: 2337.22 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 23:34:23,713 epoch 2 - iter 1470/1476 - loss 0.12844708 - time (sec): 71.44 - samples/sec: 2322.32 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 23:34:24,002 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 23:34:24,002 EPOCH 2 done: loss 0.1282 - lr: 0.000027
101
+ 2023-10-17 23:34:35,709 DEV : loss 0.11762264370918274 - f1-score (micro avg) 0.8046
102
+ 2023-10-17 23:34:35,743 saving best model
103
+ 2023-10-17 23:34:36,184 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 23:34:43,287 epoch 3 - iter 147/1476 - loss 0.06016337 - time (sec): 7.10 - samples/sec: 2283.90 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 23:34:50,147 epoch 3 - iter 294/1476 - loss 0.06475612 - time (sec): 13.96 - samples/sec: 2305.25 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 23:34:57,519 epoch 3 - iter 441/1476 - loss 0.07116651 - time (sec): 21.33 - samples/sec: 2292.73 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 23:35:04,498 epoch 3 - iter 588/1476 - loss 0.08196817 - time (sec): 28.31 - samples/sec: 2283.52 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 23:35:11,873 epoch 3 - iter 735/1476 - loss 0.08093682 - time (sec): 35.69 - samples/sec: 2309.40 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 23:35:18,750 epoch 3 - iter 882/1476 - loss 0.08196150 - time (sec): 42.56 - samples/sec: 2308.17 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 23:35:26,053 epoch 3 - iter 1029/1476 - loss 0.08435209 - time (sec): 49.87 - samples/sec: 2333.52 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 23:35:33,011 epoch 3 - iter 1176/1476 - loss 0.08397687 - time (sec): 56.83 - samples/sec: 2329.78 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 23:35:40,077 epoch 3 - iter 1323/1476 - loss 0.08214585 - time (sec): 63.89 - samples/sec: 2328.49 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 23:35:47,311 epoch 3 - iter 1470/1476 - loss 0.08451257 - time (sec): 71.13 - samples/sec: 2332.43 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 23:35:47,583 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 23:35:47,583 EPOCH 3 done: loss 0.0845 - lr: 0.000023
116
+ 2023-10-17 23:35:59,745 DEV : loss 0.12455519288778305 - f1-score (micro avg) 0.8311
117
+ 2023-10-17 23:35:59,780 saving best model
118
+ 2023-10-17 23:36:00,314 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 23:36:07,595 epoch 4 - iter 147/1476 - loss 0.04135825 - time (sec): 7.28 - samples/sec: 2357.87 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 23:36:14,807 epoch 4 - iter 294/1476 - loss 0.06168456 - time (sec): 14.49 - samples/sec: 2251.52 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 23:36:22,206 epoch 4 - iter 441/1476 - loss 0.06131877 - time (sec): 21.89 - samples/sec: 2331.92 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 23:36:29,354 epoch 4 - iter 588/1476 - loss 0.06322859 - time (sec): 29.03 - samples/sec: 2356.02 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 23:36:36,295 epoch 4 - iter 735/1476 - loss 0.05963841 - time (sec): 35.98 - samples/sec: 2326.66 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 23:36:43,129 epoch 4 - iter 882/1476 - loss 0.06022421 - time (sec): 42.81 - samples/sec: 2302.29 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 23:36:50,355 epoch 4 - iter 1029/1476 - loss 0.05910469 - time (sec): 50.03 - samples/sec: 2309.56 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 23:36:57,678 epoch 4 - iter 1176/1476 - loss 0.05977555 - time (sec): 57.36 - samples/sec: 2308.40 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 23:37:04,755 epoch 4 - iter 1323/1476 - loss 0.05955432 - time (sec): 64.44 - samples/sec: 2296.44 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 23:37:12,241 epoch 4 - iter 1470/1476 - loss 0.05887704 - time (sec): 71.92 - samples/sec: 2306.74 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 23:37:12,500 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 23:37:12,501 EPOCH 4 done: loss 0.0589 - lr: 0.000020
131
+ 2023-10-17 23:37:24,145 DEV : loss 0.17298074066638947 - f1-score (micro avg) 0.8363
132
+ 2023-10-17 23:37:24,177 saving best model
133
+ 2023-10-17 23:37:24,717 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 23:37:32,262 epoch 5 - iter 147/1476 - loss 0.03294191 - time (sec): 7.54 - samples/sec: 2111.85 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-17 23:37:39,929 epoch 5 - iter 294/1476 - loss 0.03494477 - time (sec): 15.21 - samples/sec: 2088.58 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 23:37:46,973 epoch 5 - iter 441/1476 - loss 0.03478031 - time (sec): 22.25 - samples/sec: 2167.73 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 23:37:54,339 epoch 5 - iter 588/1476 - loss 0.03960322 - time (sec): 29.62 - samples/sec: 2201.89 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-17 23:38:01,526 epoch 5 - iter 735/1476 - loss 0.03902751 - time (sec): 36.81 - samples/sec: 2204.17 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 23:38:09,120 epoch 5 - iter 882/1476 - loss 0.03994877 - time (sec): 44.40 - samples/sec: 2276.31 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 23:38:16,476 epoch 5 - iter 1029/1476 - loss 0.03929098 - time (sec): 51.76 - samples/sec: 2292.19 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-17 23:38:23,357 epoch 5 - iter 1176/1476 - loss 0.03869095 - time (sec): 58.64 - samples/sec: 2282.48 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 23:38:29,950 epoch 5 - iter 1323/1476 - loss 0.03956085 - time (sec): 65.23 - samples/sec: 2267.36 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 23:38:37,204 epoch 5 - iter 1470/1476 - loss 0.03973073 - time (sec): 72.49 - samples/sec: 2288.84 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-17 23:38:37,481 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 23:38:37,481 EPOCH 5 done: loss 0.0396 - lr: 0.000017
146
+ 2023-10-17 23:38:49,143 DEV : loss 0.19069240987300873 - f1-score (micro avg) 0.8347
147
+ 2023-10-17 23:38:49,173 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 23:38:56,442 epoch 6 - iter 147/1476 - loss 0.04151410 - time (sec): 7.27 - samples/sec: 2504.19 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-17 23:39:03,567 epoch 6 - iter 294/1476 - loss 0.03128771 - time (sec): 14.39 - samples/sec: 2396.11 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 23:39:10,534 epoch 6 - iter 441/1476 - loss 0.02813382 - time (sec): 21.36 - samples/sec: 2348.82 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 23:39:18,296 epoch 6 - iter 588/1476 - loss 0.02762635 - time (sec): 29.12 - samples/sec: 2410.53 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-17 23:39:25,189 epoch 6 - iter 735/1476 - loss 0.02714453 - time (sec): 36.01 - samples/sec: 2379.21 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 23:39:32,347 epoch 6 - iter 882/1476 - loss 0.02908034 - time (sec): 43.17 - samples/sec: 2358.30 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 23:39:39,421 epoch 6 - iter 1029/1476 - loss 0.02853843 - time (sec): 50.25 - samples/sec: 2369.55 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-17 23:39:46,368 epoch 6 - iter 1176/1476 - loss 0.02820722 - time (sec): 57.19 - samples/sec: 2340.90 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 23:39:53,086 epoch 6 - iter 1323/1476 - loss 0.02791306 - time (sec): 63.91 - samples/sec: 2341.08 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 23:40:00,050 epoch 6 - iter 1470/1476 - loss 0.02765959 - time (sec): 70.88 - samples/sec: 2340.75 - lr: 0.000013 - momentum: 0.000000
158
+ 2023-10-17 23:40:00,317 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 23:40:00,317 EPOCH 6 done: loss 0.0276 - lr: 0.000013
160
+ 2023-10-17 23:40:12,051 DEV : loss 0.2225208729505539 - f1-score (micro avg) 0.8227
161
+ 2023-10-17 23:40:12,083 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-17 23:40:18,908 epoch 7 - iter 147/1476 - loss 0.02536894 - time (sec): 6.82 - samples/sec: 2256.74 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-17 23:40:25,940 epoch 7 - iter 294/1476 - loss 0.01875569 - time (sec): 13.86 - samples/sec: 2297.77 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-17 23:40:32,837 epoch 7 - iter 441/1476 - loss 0.01775067 - time (sec): 20.75 - samples/sec: 2274.90 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-17 23:40:39,922 epoch 7 - iter 588/1476 - loss 0.01897025 - time (sec): 27.84 - samples/sec: 2270.43 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-17 23:40:47,381 epoch 7 - iter 735/1476 - loss 0.01918291 - time (sec): 35.30 - samples/sec: 2312.85 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 23:40:54,197 epoch 7 - iter 882/1476 - loss 0.01739317 - time (sec): 42.11 - samples/sec: 2292.26 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-17 23:41:01,472 epoch 7 - iter 1029/1476 - loss 0.02015101 - time (sec): 49.39 - samples/sec: 2297.01 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-17 23:41:08,793 epoch 7 - iter 1176/1476 - loss 0.01942613 - time (sec): 56.71 - samples/sec: 2311.05 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 23:41:15,889 epoch 7 - iter 1323/1476 - loss 0.01868802 - time (sec): 63.80 - samples/sec: 2317.14 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-17 23:41:22,978 epoch 7 - iter 1470/1476 - loss 0.01907602 - time (sec): 70.89 - samples/sec: 2336.32 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-17 23:41:23,241 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-17 23:41:23,242 EPOCH 7 done: loss 0.0190 - lr: 0.000010
174
+ 2023-10-17 23:41:34,910 DEV : loss 0.2076645791530609 - f1-score (micro avg) 0.8429
175
+ 2023-10-17 23:41:34,943 saving best model
176
+ 2023-10-17 23:41:35,534 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 23:41:42,573 epoch 8 - iter 147/1476 - loss 0.00728443 - time (sec): 7.04 - samples/sec: 2313.22 - lr: 0.000010 - momentum: 0.000000
178
+ 2023-10-17 23:41:49,364 epoch 8 - iter 294/1476 - loss 0.01155375 - time (sec): 13.83 - samples/sec: 2230.80 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-17 23:41:56,955 epoch 8 - iter 441/1476 - loss 0.00998468 - time (sec): 21.42 - samples/sec: 2288.60 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 23:42:03,926 epoch 8 - iter 588/1476 - loss 0.00978555 - time (sec): 28.39 - samples/sec: 2255.65 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-17 23:42:11,251 epoch 8 - iter 735/1476 - loss 0.01395907 - time (sec): 35.72 - samples/sec: 2310.58 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-17 23:42:18,331 epoch 8 - iter 882/1476 - loss 0.01725840 - time (sec): 42.80 - samples/sec: 2310.54 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 23:42:25,186 epoch 8 - iter 1029/1476 - loss 0.01674081 - time (sec): 49.65 - samples/sec: 2303.01 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-17 23:42:31,919 epoch 8 - iter 1176/1476 - loss 0.01586411 - time (sec): 56.38 - samples/sec: 2297.83 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-17 23:42:38,881 epoch 8 - iter 1323/1476 - loss 0.01535313 - time (sec): 63.35 - samples/sec: 2295.24 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 23:42:46,810 epoch 8 - iter 1470/1476 - loss 0.01565060 - time (sec): 71.27 - samples/sec: 2323.79 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-17 23:42:47,094 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 23:42:47,094 EPOCH 8 done: loss 0.0156 - lr: 0.000007
189
+ 2023-10-17 23:42:58,817 DEV : loss 0.1886121928691864 - f1-score (micro avg) 0.8538
190
+ 2023-10-17 23:42:58,852 saving best model
191
+ 2023-10-17 23:42:59,442 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-17 23:43:06,381 epoch 9 - iter 147/1476 - loss 0.00904489 - time (sec): 6.93 - samples/sec: 2327.73 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 23:43:13,534 epoch 9 - iter 294/1476 - loss 0.01213344 - time (sec): 14.09 - samples/sec: 2283.24 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 23:43:20,577 epoch 9 - iter 441/1476 - loss 0.00968888 - time (sec): 21.13 - samples/sec: 2369.80 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-17 23:43:27,560 epoch 9 - iter 588/1476 - loss 0.00805351 - time (sec): 28.11 - samples/sec: 2342.89 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 23:43:34,810 epoch 9 - iter 735/1476 - loss 0.00938282 - time (sec): 35.36 - samples/sec: 2362.91 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 23:43:41,875 epoch 9 - iter 882/1476 - loss 0.01116852 - time (sec): 42.43 - samples/sec: 2338.20 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-17 23:43:48,777 epoch 9 - iter 1029/1476 - loss 0.01064119 - time (sec): 49.33 - samples/sec: 2324.47 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 23:43:56,251 epoch 9 - iter 1176/1476 - loss 0.00962622 - time (sec): 56.80 - samples/sec: 2329.48 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 23:44:03,238 epoch 9 - iter 1323/1476 - loss 0.00924438 - time (sec): 63.79 - samples/sec: 2329.34 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-17 23:44:10,398 epoch 9 - iter 1470/1476 - loss 0.00894017 - time (sec): 70.95 - samples/sec: 2327.45 - lr: 0.000003 - momentum: 0.000000
202
+ 2023-10-17 23:44:10,806 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 23:44:10,806 EPOCH 9 done: loss 0.0089 - lr: 0.000003
204
+ 2023-10-17 23:44:22,347 DEV : loss 0.20553840696811676 - f1-score (micro avg) 0.8585
205
+ 2023-10-17 23:44:22,380 saving best model
206
+ 2023-10-17 23:44:22,978 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 23:44:30,453 epoch 10 - iter 147/1476 - loss 0.00318820 - time (sec): 7.47 - samples/sec: 2363.28 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 23:44:37,552 epoch 10 - iter 294/1476 - loss 0.00833510 - time (sec): 14.57 - samples/sec: 2359.01 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 23:44:44,723 epoch 10 - iter 441/1476 - loss 0.00762237 - time (sec): 21.74 - samples/sec: 2327.59 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 23:44:52,236 epoch 10 - iter 588/1476 - loss 0.00924017 - time (sec): 29.26 - samples/sec: 2352.49 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 23:44:59,478 epoch 10 - iter 735/1476 - loss 0.00768338 - time (sec): 36.50 - samples/sec: 2325.80 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 23:45:06,600 epoch 10 - iter 882/1476 - loss 0.00673783 - time (sec): 43.62 - samples/sec: 2327.48 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 23:45:13,489 epoch 10 - iter 1029/1476 - loss 0.00625813 - time (sec): 50.51 - samples/sec: 2314.98 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 23:45:20,557 epoch 10 - iter 1176/1476 - loss 0.00604069 - time (sec): 57.58 - samples/sec: 2306.39 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 23:45:27,808 epoch 10 - iter 1323/1476 - loss 0.00615467 - time (sec): 64.83 - samples/sec: 2301.76 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-17 23:45:34,888 epoch 10 - iter 1470/1476 - loss 0.00646005 - time (sec): 71.91 - samples/sec: 2306.16 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 23:45:35,144 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 23:45:35,144 EPOCH 10 done: loss 0.0064 - lr: 0.000000
219
+ 2023-10-17 23:45:46,863 DEV : loss 0.20840205252170563 - f1-score (micro avg) 0.8595
220
+ 2023-10-17 23:45:46,900 saving best model
221
+ 2023-10-17 23:45:47,919 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-17 23:45:47,920 Loading model from best epoch ...
223
+ 2023-10-17 23:45:49,391 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
224
+ 2023-10-17 23:45:56,118
225
+ Results:
226
+ - F-score (micro) 0.8122
227
+ - F-score (macro) 0.7254
228
+ - Accuracy 0.7022
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ loc 0.8730 0.8811 0.8770 858
234
+ pers 0.7660 0.8045 0.7847 537
235
+ org 0.6357 0.6212 0.6284 132
236
+ prod 0.7458 0.7213 0.7333 61
237
+ time 0.5645 0.6481 0.6034 54
238
+
239
+ micro avg 0.8030 0.8216 0.8122 1642
240
+ macro avg 0.7170 0.7353 0.7254 1642
241
+ weighted avg 0.8040 0.8216 0.8125 1642
242
+
243
+ 2023-10-17 23:45:56,118 ----------------------------------------------------------------------------------------------------