Hugging Face's logo

hmteams
/
flair-hipe-2022-hipe2020-fr

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
52d7712
•
1 Parent(s): 187a685

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.1697571822.bce904bcef33.2482.0 +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 sha256:828ba32180b6ebd906e647aeb974e58303f62285800333530f1d78b7d139c9d2
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 19:44:41 0.0000 0.6742 0.1234 0.7397 0.7715 0.7553 0.6315
3
+ 2 19:45:46 0.0000 0.1220 0.0958 0.7816 0.8505 0.8146 0.7085
4
+ 3 19:46:51 0.0000 0.0722 0.1058 0.8130 0.8540 0.8330 0.7356
5
+ 4 19:47:55 0.0000 0.0485 0.1227 0.8392 0.8580 0.8485 0.7566
6
+ 5 19:48:59 0.0000 0.0335 0.1517 0.8440 0.8648 0.8543 0.7732
7
+ 6 19:50:05 0.0000 0.0246 0.1573 0.8487 0.8608 0.8547 0.7716
8
+ 7 19:51:09 0.0000 0.0183 0.1808 0.8605 0.8688 0.8646 0.7783
9
+ 8 19:52:15 0.0000 0.0126 0.1948 0.8585 0.8620 0.8602 0.7786
10
+ 9 19:53:18 0.0000 0.0095 0.1867 0.8567 0.8631 0.8599 0.7792
11
+ 10 19:54:20 0.0000 0.0067 0.1856 0.8628 0.8677 0.8652 0.7862
runs/events.out.tfevents.1697571822.bce904bcef33.2482.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c730a6a574007b737721a1663386469a7469caf5bfd66c761f69bc80e4371b
3
+ size 415388
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 19:43:42,471 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 19:43:42,472 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 19:43:42,472 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 19:43:42,472 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 19:43:42,472 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 19:43:42,472 Train: 5901 sentences
51
+ 2023-10-17 19:43:42,472 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 19:43:42,472 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 19:43:42,472 Training Params:
54
+ 2023-10-17 19:43:42,473 - learning_rate: "3e-05"
55
+ 2023-10-17 19:43:42,473 - mini_batch_size: "8"
56
+ 2023-10-17 19:43:42,473 - max_epochs: "10"
57
+ 2023-10-17 19:43:42,473 - shuffle: "True"
58
+ 2023-10-17 19:43:42,473 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 19:43:42,473 Plugins:
60
+ 2023-10-17 19:43:42,473 - TensorboardLogger
61
+ 2023-10-17 19:43:42,473 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 19:43:42,473 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 19:43:42,473 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 19:43:42,473 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 19:43:42,473 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 19:43:42,473 Computation:
67
+ 2023-10-17 19:43:42,473 - compute on device: cuda:0
68
+ 2023-10-17 19:43:42,473 - embedding storage: none
69
+ 2023-10-17 19:43:42,473 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 19:43:42,473 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
71
+ 2023-10-17 19:43:42,473 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 19:43:42,473 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 19:43:42,473 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 19:43:48,751 epoch 1 - iter 73/738 - loss 3.18129576 - time (sec): 6.28 - samples/sec: 2801.48 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 19:43:53,251 epoch 1 - iter 146/738 - loss 2.19020696 - time (sec): 10.78 - samples/sec: 3050.59 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 19:43:59,111 epoch 1 - iter 219/738 - loss 1.59513825 - time (sec): 16.64 - samples/sec: 3079.50 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 19:44:05,045 epoch 1 - iter 292/738 - loss 1.27764894 - time (sec): 22.57 - samples/sec: 3059.98 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 19:44:10,208 epoch 1 - iter 365/738 - loss 1.09648871 - time (sec): 27.73 - samples/sec: 3067.33 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 19:44:14,907 epoch 1 - iter 438/738 - loss 0.97918922 - time (sec): 32.43 - samples/sec: 3080.33 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 19:44:19,805 epoch 1 - iter 511/738 - loss 0.88580507 - time (sec): 37.33 - samples/sec: 3085.82 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 19:44:24,890 epoch 1 - iter 584/738 - loss 0.80554273 - time (sec): 42.42 - samples/sec: 3097.71 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 19:44:30,040 epoch 1 - iter 657/738 - loss 0.73810377 - time (sec): 47.57 - samples/sec: 3101.81 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 19:44:35,093 epoch 1 - iter 730/738 - loss 0.67997669 - time (sec): 52.62 - samples/sec: 3129.86 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 19:44:35,557 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 19:44:35,557 EPOCH 1 done: loss 0.6742 - lr: 0.000030
86
+ 2023-10-17 19:44:41,721 DEV : loss 0.12336786091327667 - f1-score (micro avg) 0.7553
87
+ 2023-10-17 19:44:41,759 saving best model
88
+ 2023-10-17 19:44:42,193 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 19:44:48,004 epoch 2 - iter 73/738 - loss 0.15982108 - time (sec): 5.81 - samples/sec: 2868.17 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 19:44:53,384 epoch 2 - iter 146/738 - loss 0.15219823 - time (sec): 11.19 - samples/sec: 3108.03 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 19:44:58,736 epoch 2 - iter 219/738 - loss 0.14354631 - time (sec): 16.54 - samples/sec: 3140.24 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 19:45:03,750 epoch 2 - iter 292/738 - loss 0.13970635 - time (sec): 21.55 - samples/sec: 3123.54 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 19:45:08,549 epoch 2 - iter 365/738 - loss 0.13505059 - time (sec): 26.35 - samples/sec: 3108.53 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 19:45:13,319 epoch 2 - iter 438/738 - loss 0.13319422 - time (sec): 31.12 - samples/sec: 3120.46 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 19:45:18,429 epoch 2 - iter 511/738 - loss 0.12880087 - time (sec): 36.23 - samples/sec: 3131.97 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 19:45:23,596 epoch 2 - iter 584/738 - loss 0.12583910 - time (sec): 41.40 - samples/sec: 3127.20 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 19:45:29,201 epoch 2 - iter 657/738 - loss 0.12490350 - time (sec): 47.01 - samples/sec: 3139.13 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 19:45:34,718 epoch 2 - iter 730/738 - loss 0.12241339 - time (sec): 52.52 - samples/sec: 3133.31 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 19:45:35,417 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 19:45:35,417 EPOCH 2 done: loss 0.1220 - lr: 0.000027
101
+ 2023-10-17 19:45:46,937 DEV : loss 0.09578868746757507 - f1-score (micro avg) 0.8146
102
+ 2023-10-17 19:45:46,965 saving best model
103
+ 2023-10-17 19:45:47,493 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 19:45:53,270 epoch 3 - iter 73/738 - loss 0.07059181 - time (sec): 5.77 - samples/sec: 3049.57 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 19:45:58,525 epoch 3 - iter 146/738 - loss 0.07590889 - time (sec): 11.03 - samples/sec: 3161.90 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 19:46:03,634 epoch 3 - iter 219/738 - loss 0.07091362 - time (sec): 16.14 - samples/sec: 3199.78 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 19:46:08,697 epoch 3 - iter 292/738 - loss 0.06883331 - time (sec): 21.20 - samples/sec: 3180.84 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 19:46:13,735 epoch 3 - iter 365/738 - loss 0.07059965 - time (sec): 26.24 - samples/sec: 3176.95 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 19:46:18,955 epoch 3 - iter 438/738 - loss 0.07205663 - time (sec): 31.46 - samples/sec: 3143.20 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 19:46:24,569 epoch 3 - iter 511/738 - loss 0.07270546 - time (sec): 37.07 - samples/sec: 3157.14 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 19:46:29,790 epoch 3 - iter 584/738 - loss 0.07234630 - time (sec): 42.29 - samples/sec: 3145.32 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 19:46:34,895 epoch 3 - iter 657/738 - loss 0.07186579 - time (sec): 47.40 - samples/sec: 3143.08 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 19:46:39,719 epoch 3 - iter 730/738 - loss 0.07250374 - time (sec): 52.22 - samples/sec: 3159.36 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 19:46:40,195 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 19:46:40,195 EPOCH 3 done: loss 0.0722 - lr: 0.000023
116
+ 2023-10-17 19:46:51,335 DEV : loss 0.10583800822496414 - f1-score (micro avg) 0.833
117
+ 2023-10-17 19:46:51,364 saving best model
118
+ 2023-10-17 19:46:51,881 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 19:46:57,112 epoch 4 - iter 73/738 - loss 0.05206689 - time (sec): 5.23 - samples/sec: 3037.15 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 19:47:02,454 epoch 4 - iter 146/738 - loss 0.04622094 - time (sec): 10.57 - samples/sec: 3169.54 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 19:47:07,164 epoch 4 - iter 219/738 - loss 0.05037936 - time (sec): 15.28 - samples/sec: 3196.93 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 19:47:12,269 epoch 4 - iter 292/738 - loss 0.05234898 - time (sec): 20.39 - samples/sec: 3188.25 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 19:47:17,049 epoch 4 - iter 365/738 - loss 0.05275237 - time (sec): 25.17 - samples/sec: 3168.35 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 19:47:22,024 epoch 4 - iter 438/738 - loss 0.05040956 - time (sec): 30.14 - samples/sec: 3198.64 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 19:47:26,845 epoch 4 - iter 511/738 - loss 0.04932344 - time (sec): 34.96 - samples/sec: 3209.89 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 19:47:32,525 epoch 4 - iter 584/738 - loss 0.04781680 - time (sec): 40.64 - samples/sec: 3196.99 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 19:47:37,836 epoch 4 - iter 657/738 - loss 0.04819721 - time (sec): 45.95 - samples/sec: 3181.08 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 19:47:43,898 epoch 4 - iter 730/738 - loss 0.04886480 - time (sec): 52.02 - samples/sec: 3167.06 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 19:47:44,407 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 19:47:44,407 EPOCH 4 done: loss 0.0485 - lr: 0.000020
131
+ 2023-10-17 19:47:55,491 DEV : loss 0.122743621468544 - f1-score (micro avg) 0.8485
132
+ 2023-10-17 19:47:55,519 saving best model
133
+ 2023-10-17 19:47:56,054 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 19:48:01,493 epoch 5 - iter 73/738 - loss 0.02654138 - time (sec): 5.44 - samples/sec: 3265.24 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-17 19:48:06,555 epoch 5 - iter 146/738 - loss 0.03073291 - time (sec): 10.50 - samples/sec: 3185.99 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 19:48:11,730 epoch 5 - iter 219/738 - loss 0.03108548 - time (sec): 15.67 - samples/sec: 3161.54 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 19:48:16,908 epoch 5 - iter 292/738 - loss 0.03530107 - time (sec): 20.85 - samples/sec: 3182.99 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-17 19:48:21,927 epoch 5 - iter 365/738 - loss 0.03345830 - time (sec): 25.87 - samples/sec: 3204.30 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 19:48:27,157 epoch 5 - iter 438/738 - loss 0.03329768 - time (sec): 31.10 - samples/sec: 3199.94 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 19:48:32,613 epoch 5 - iter 511/738 - loss 0.03272234 - time (sec): 36.56 - samples/sec: 3155.39 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-17 19:48:37,419 epoch 5 - iter 584/738 - loss 0.03290570 - time (sec): 41.36 - samples/sec: 3159.03 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 19:48:42,520 epoch 5 - iter 657/738 - loss 0.03309942 - time (sec): 46.46 - samples/sec: 3171.10 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 19:48:47,829 epoch 5 - iter 730/738 - loss 0.03334347 - time (sec): 51.77 - samples/sec: 3170.29 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-17 19:48:48,658 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 19:48:48,658 EPOCH 5 done: loss 0.0335 - lr: 0.000017
146
+ 2023-10-17 19:48:59,704 DEV : loss 0.15168806910514832 - f1-score (micro avg) 0.8543
147
+ 2023-10-17 19:48:59,733 saving best model
148
+ 2023-10-17 19:49:00,281 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 19:49:05,290 epoch 6 - iter 73/738 - loss 0.03010752 - time (sec): 5.01 - samples/sec: 3140.40 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 19:49:10,877 epoch 6 - iter 146/738 - loss 0.02499735 - time (sec): 10.59 - samples/sec: 3101.45 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 19:49:16,327 epoch 6 - iter 219/738 - loss 0.02175671 - time (sec): 16.05 - samples/sec: 3082.57 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-17 19:49:21,571 epoch 6 - iter 292/738 - loss 0.02484654 - time (sec): 21.29 - samples/sec: 3068.11 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 19:49:26,919 epoch 6 - iter 365/738 - loss 0.02430030 - time (sec): 26.64 - samples/sec: 3058.19 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 19:49:32,199 epoch 6 - iter 438/738 - loss 0.02418786 - time (sec): 31.92 - samples/sec: 3041.81 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-17 19:49:37,745 epoch 6 - iter 511/738 - loss 0.02390168 - time (sec): 37.46 - samples/sec: 3036.04 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 19:49:42,959 epoch 6 - iter 584/738 - loss 0.02289941 - time (sec): 42.68 - samples/sec: 3066.21 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 19:49:48,171 epoch 6 - iter 657/738 - loss 0.02342068 - time (sec): 47.89 - samples/sec: 3066.73 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-17 19:49:53,684 epoch 6 - iter 730/738 - loss 0.02460435 - time (sec): 53.40 - samples/sec: 3080.94 - lr: 0.000013 - momentum: 0.000000
159
+ 2023-10-17 19:49:54,408 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 19:49:54,408 EPOCH 6 done: loss 0.0246 - lr: 0.000013
161
+ 2023-10-17 19:50:05,542 DEV : loss 0.15729978680610657 - f1-score (micro avg) 0.8547
162
+ 2023-10-17 19:50:05,573 saving best model
163
+ 2023-10-17 19:50:06,189 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 19:50:11,582 epoch 7 - iter 73/738 - loss 0.01280464 - time (sec): 5.39 - samples/sec: 3121.20 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-17 19:50:16,753 epoch 7 - iter 146/738 - loss 0.01448297 - time (sec): 10.56 - samples/sec: 3123.91 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-17 19:50:22,379 epoch 7 - iter 219/738 - loss 0.01626473 - time (sec): 16.18 - samples/sec: 3133.78 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 19:50:27,912 epoch 7 - iter 292/738 - loss 0.01707587 - time (sec): 21.72 - samples/sec: 3140.88 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-17 19:50:33,061 epoch 7 - iter 365/738 - loss 0.01952204 - time (sec): 26.87 - samples/sec: 3121.60 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-17 19:50:38,280 epoch 7 - iter 438/738 - loss 0.01973386 - time (sec): 32.09 - samples/sec: 3134.20 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 19:50:43,038 epoch 7 - iter 511/738 - loss 0.01921562 - time (sec): 36.84 - samples/sec: 3158.94 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-17 19:50:48,334 epoch 7 - iter 584/738 - loss 0.01911006 - time (sec): 42.14 - samples/sec: 3166.35 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-17 19:50:53,630 epoch 7 - iter 657/738 - loss 0.01943647 - time (sec): 47.44 - samples/sec: 3163.17 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-17 19:50:58,375 epoch 7 - iter 730/738 - loss 0.01835721 - time (sec): 52.18 - samples/sec: 3160.70 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-17 19:50:58,850 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 19:50:58,850 EPOCH 7 done: loss 0.0183 - lr: 0.000010
176
+ 2023-10-17 19:51:09,961 DEV : loss 0.18084457516670227 - f1-score (micro avg) 0.8646
177
+ 2023-10-17 19:51:09,994 saving best model
178
+ 2023-10-17 19:51:10,719 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-17 19:51:15,879 epoch 8 - iter 73/738 - loss 0.00764996 - time (sec): 5.16 - samples/sec: 3152.05 - lr: 0.000010 - momentum: 0.000000
180
+ 2023-10-17 19:51:22,133 epoch 8 - iter 146/738 - loss 0.01104963 - time (sec): 11.41 - samples/sec: 2973.21 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-17 19:51:27,099 epoch 8 - iter 219/738 - loss 0.01198235 - time (sec): 16.38 - samples/sec: 3023.19 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-17 19:51:32,039 epoch 8 - iter 292/738 - loss 0.01113988 - time (sec): 21.32 - samples/sec: 3063.31 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-17 19:51:37,404 epoch 8 - iter 365/738 - loss 0.01216710 - time (sec): 26.68 - samples/sec: 3071.41 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-17 19:51:42,200 epoch 8 - iter 438/738 - loss 0.01124920 - time (sec): 31.48 - samples/sec: 3103.15 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-17 19:51:48,209 epoch 8 - iter 511/738 - loss 0.01270444 - time (sec): 37.49 - samples/sec: 3113.35 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-17 19:51:53,103 epoch 8 - iter 584/738 - loss 0.01213295 - time (sec): 42.38 - samples/sec: 3133.78 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-17 19:51:58,181 epoch 8 - iter 657/738 - loss 0.01173209 - time (sec): 47.46 - samples/sec: 3143.35 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-17 19:52:03,086 epoch 8 - iter 730/738 - loss 0.01264595 - time (sec): 52.37 - samples/sec: 3142.90 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-17 19:52:03,702 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 19:52:03,702 EPOCH 8 done: loss 0.0126 - lr: 0.000007
191
+ 2023-10-17 19:52:15,277 DEV : loss 0.19484567642211914 - f1-score (micro avg) 0.8602
192
+ 2023-10-17 19:52:15,312 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 19:52:20,982 epoch 9 - iter 73/738 - loss 0.00488093 - time (sec): 5.67 - samples/sec: 3162.54 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 19:52:26,399 epoch 9 - iter 146/738 - loss 0.00805781 - time (sec): 11.09 - samples/sec: 3264.48 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-17 19:52:32,156 epoch 9 - iter 219/738 - loss 0.00865579 - time (sec): 16.84 - samples/sec: 3235.87 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-17 19:52:37,449 epoch 9 - iter 292/738 - loss 0.00824878 - time (sec): 22.14 - samples/sec: 3143.10 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 19:52:42,684 epoch 9 - iter 365/738 - loss 0.00755746 - time (sec): 27.37 - samples/sec: 3121.26 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-17 19:52:47,474 epoch 9 - iter 438/738 - loss 0.00745069 - time (sec): 32.16 - samples/sec: 3162.12 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-17 19:52:52,032 epoch 9 - iter 511/738 - loss 0.00907204 - time (sec): 36.72 - samples/sec: 3177.35 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 19:52:56,789 epoch 9 - iter 584/738 - loss 0.00911722 - time (sec): 41.48 - samples/sec: 3186.87 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-17 19:53:02,404 epoch 9 - iter 657/738 - loss 0.00897147 - time (sec): 47.09 - samples/sec: 3187.92 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-17 19:53:06,847 epoch 9 - iter 730/738 - loss 0.00954450 - time (sec): 51.53 - samples/sec: 3191.40 - lr: 0.000003 - momentum: 0.000000
203
+ 2023-10-17 19:53:07,402 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 19:53:07,402 EPOCH 9 done: loss 0.0095 - lr: 0.000003
205
+ 2023-10-17 19:53:18,725 DEV : loss 0.1866709142923355 - f1-score (micro avg) 0.8599
206
+ 2023-10-17 19:53:18,756 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 19:53:24,448 epoch 10 - iter 73/738 - loss 0.00755432 - time (sec): 5.69 - samples/sec: 3440.94 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 19:53:29,523 epoch 10 - iter 146/738 - loss 0.00658582 - time (sec): 10.77 - samples/sec: 3419.43 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 19:53:34,251 epoch 10 - iter 219/738 - loss 0.00573246 - time (sec): 15.49 - samples/sec: 3424.02 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 19:53:38,964 epoch 10 - iter 292/738 - loss 0.00503723 - time (sec): 20.21 - samples/sec: 3347.86 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 19:53:43,952 epoch 10 - iter 365/738 - loss 0.00546895 - time (sec): 25.19 - samples/sec: 3299.09 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 19:53:48,719 epoch 10 - iter 438/738 - loss 0.00520885 - time (sec): 29.96 - samples/sec: 3314.36 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 19:53:54,231 epoch 10 - iter 511/738 - loss 0.00544848 - time (sec): 35.47 - samples/sec: 3288.43 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 19:53:58,768 epoch 10 - iter 584/738 - loss 0.00613301 - time (sec): 40.01 - samples/sec: 3293.93 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 19:54:03,447 epoch 10 - iter 657/738 - loss 0.00650287 - time (sec): 44.69 - samples/sec: 3300.55 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-17 19:54:08,736 epoch 10 - iter 730/738 - loss 0.00664178 - time (sec): 49.98 - samples/sec: 3299.34 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 19:54:09,185 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 19:54:09,185 EPOCH 10 done: loss 0.0067 - lr: 0.000000
219
+ 2023-10-17 19:54:20,252 DEV : loss 0.1855737715959549 - f1-score (micro avg) 0.8652
220
+ 2023-10-17 19:54:20,280 saving best model
221
+ 2023-10-17 19:54:21,202 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-17 19:54:21,204 Loading model from best epoch ...
223
+ 2023-10-17 19:54:23,111 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 19:54:29,618
225
+ Results:
226
+ - F-score (micro) 0.8059
227
+ - F-score (macro) 0.7164
228
+ - Accuracy 0.6929
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ loc 0.8570 0.8800 0.8683 858
234
+ pers 0.7792 0.8082 0.7934 537
235
+ org 0.5467 0.6212 0.5816 132
236
+ prod 0.7679 0.7049 0.7350 61
237
+ time 0.5645 0.6481 0.6034 54
238
+
239
+ micro avg 0.7907 0.8216 0.8059 1642
240
+ macro avg 0.7030 0.7325 0.7164 1642
241
+ weighted avg 0.7937 0.8216 0.8071 1642
242
+
243
+ 2023-10-17 19:54:29,618 ----------------------------------------------------------------------------------------------------