Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert_tiny-bs8-wsFalse-e10-lr3e-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
74c6741
•
1 Parent(s): a31d8ee

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.1697655172.46dc0c540dd0.3108.2 +3 -0
  5. test.tsv +0 -0
  6. training.log +247 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111d56ab3061c2ceb3b4f31bb7975422479cc3c80c893ac23506d040c7077b7b
3
+ size 19050210
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 18:53:13 0.0000 1.6503 0.4868 0.0000 0.0000 0.0000 0.0000
3
+ 2 18:53:38 0.0000 0.4785 0.3400 0.2854 0.2583 0.2712 0.1671
4
+ 3 18:54:02 0.0000 0.3998 0.3054 0.2904 0.3562 0.3200 0.2034
5
+ 4 18:54:27 0.0000 0.3663 0.2950 0.3345 0.3866 0.3587 0.2345
6
+ 5 18:54:53 0.0000 0.3400 0.2756 0.3527 0.4267 0.3862 0.2582
7
+ 6 18:55:18 0.0000 0.3219 0.2664 0.3876 0.4456 0.4146 0.2820
8
+ 7 18:55:43 0.0000 0.3074 0.2636 0.3828 0.4473 0.4126 0.2794
9
+ 8 18:56:07 0.0000 0.2999 0.2585 0.3942 0.4674 0.4277 0.2933
10
+ 9 18:56:32 0.0000 0.2950 0.2576 0.4037 0.4622 0.4310 0.2967
11
+ 10 18:56:57 0.0000 0.2885 0.2571 0.4034 0.4685 0.4335 0.2988
runs/events.out.tfevents.1697655172.46dc0c540dd0.3108.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c961398b86d1168f9dac94d8115de8b49732502f390c4870a4a71fd87028d8
3
+ size 415388
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 18:52:52,741 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 18:52:52,741 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-18 18:52:52,741 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 18:52:52,742 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
52
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
53
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 18:52:52,742 Train: 5901 sentences
55
+ 2023-10-18 18:52:52,742 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 18:52:52,742 Training Params:
58
+ 2023-10-18 18:52:52,742 - learning_rate: "3e-05"
59
+ 2023-10-18 18:52:52,742 - mini_batch_size: "8"
60
+ 2023-10-18 18:52:52,742 - max_epochs: "10"
61
+ 2023-10-18 18:52:52,742 - shuffle: "True"
62
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 18:52:52,742 Plugins:
64
+ 2023-10-18 18:52:52,742 - TensorboardLogger
65
+ 2023-10-18 18:52:52,742 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 18:52:52,742 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 18:52:52,742 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 18:52:52,742 Computation:
71
+ 2023-10-18 18:52:52,742 - compute on device: cuda:0
72
+ 2023-10-18 18:52:52,742 - embedding storage: none
73
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 18:52:52,742 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 18:52:52,742 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 18:52:52,742 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 18:52:54,502 epoch 1 - iter 73/738 - loss 3.81874353 - time (sec): 1.76 - samples/sec: 9383.08 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 18:52:56,284 epoch 1 - iter 146/738 - loss 3.68234957 - time (sec): 3.54 - samples/sec: 8933.75 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 18:52:58,194 epoch 1 - iter 219/738 - loss 3.37630765 - time (sec): 5.45 - samples/sec: 9239.17 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 18:52:59,863 epoch 1 - iter 292/738 - loss 3.02254508 - time (sec): 7.12 - samples/sec: 9456.64 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 18:53:01,582 epoch 1 - iter 365/738 - loss 2.66170049 - time (sec): 8.84 - samples/sec: 9361.30 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 18:53:03,272 epoch 1 - iter 438/738 - loss 2.36532082 - time (sec): 10.53 - samples/sec: 9328.38 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 18:53:05,062 epoch 1 - iter 511/738 - loss 2.11033803 - time (sec): 12.32 - samples/sec: 9374.21 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 18:53:06,754 epoch 1 - iter 584/738 - loss 1.93341360 - time (sec): 14.01 - samples/sec: 9374.65 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 18:53:08,399 epoch 1 - iter 657/738 - loss 1.79640058 - time (sec): 15.66 - samples/sec: 9356.30 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 18:53:10,201 epoch 1 - iter 730/738 - loss 1.66035043 - time (sec): 17.46 - samples/sec: 9446.21 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-18 18:53:10,377 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 18:53:10,377 EPOCH 1 done: loss 1.6503 - lr: 0.000030
90
+ 2023-10-18 18:53:13,137 DEV : loss 0.48679542541503906 - f1-score (micro avg) 0.0
91
+ 2023-10-18 18:53:13,162 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 18:53:14,888 epoch 2 - iter 73/738 - loss 0.53428200 - time (sec): 1.73 - samples/sec: 9434.51 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 18:53:16,772 epoch 2 - iter 146/738 - loss 0.53407256 - time (sec): 3.61 - samples/sec: 9471.60 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 18:53:18,686 epoch 2 - iter 219/738 - loss 0.52996403 - time (sec): 5.52 - samples/sec: 9495.57 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 18:53:20,509 epoch 2 - iter 292/738 - loss 0.53131590 - time (sec): 7.35 - samples/sec: 9415.99 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 18:53:22,170 epoch 2 - iter 365/738 - loss 0.52158207 - time (sec): 9.01 - samples/sec: 9329.11 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 18:53:23,928 epoch 2 - iter 438/738 - loss 0.51558366 - time (sec): 10.77 - samples/sec: 9362.28 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 18:53:25,719 epoch 2 - iter 511/738 - loss 0.49662623 - time (sec): 12.56 - samples/sec: 9450.83 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 18:53:27,382 epoch 2 - iter 584/738 - loss 0.49077712 - time (sec): 14.22 - samples/sec: 9407.95 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 18:53:29,071 epoch 2 - iter 657/738 - loss 0.48484877 - time (sec): 15.91 - samples/sec: 9359.70 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 18:53:30,846 epoch 2 - iter 730/738 - loss 0.47901795 - time (sec): 17.68 - samples/sec: 9310.89 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 18:53:31,028 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 18:53:31,029 EPOCH 2 done: loss 0.4785 - lr: 0.000027
104
+ 2023-10-18 18:53:38,087 DEV : loss 0.33998891711235046 - f1-score (micro avg) 0.2712
105
+ 2023-10-18 18:53:38,113 saving best model
106
+ 2023-10-18 18:53:38,141 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 18:53:39,865 epoch 3 - iter 73/738 - loss 0.40935465 - time (sec): 1.72 - samples/sec: 9824.36 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 18:53:41,684 epoch 3 - iter 146/738 - loss 0.41668843 - time (sec): 3.54 - samples/sec: 9634.44 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 18:53:43,431 epoch 3 - iter 219/738 - loss 0.41715597 - time (sec): 5.29 - samples/sec: 9480.32 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-18 18:53:45,146 epoch 3 - iter 292/738 - loss 0.41227420 - time (sec): 7.00 - samples/sec: 9447.71 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 18:53:46,726 epoch 3 - iter 365/738 - loss 0.41105667 - time (sec): 8.58 - samples/sec: 9313.13 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 18:53:48,446 epoch 3 - iter 438/738 - loss 0.40654280 - time (sec): 10.30 - samples/sec: 9335.83 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-18 18:53:50,257 epoch 3 - iter 511/738 - loss 0.39785791 - time (sec): 12.11 - samples/sec: 9328.86 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 18:53:52,055 epoch 3 - iter 584/738 - loss 0.39819890 - time (sec): 13.91 - samples/sec: 9430.47 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 18:53:53,814 epoch 3 - iter 657/738 - loss 0.39752472 - time (sec): 15.67 - samples/sec: 9377.86 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-18 18:53:55,587 epoch 3 - iter 730/738 - loss 0.39992408 - time (sec): 17.45 - samples/sec: 9426.87 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-18 18:53:55,783 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 18:53:55,784 EPOCH 3 done: loss 0.3998 - lr: 0.000023
119
+ 2023-10-18 18:54:02,909 DEV : loss 0.30542612075805664 - f1-score (micro avg) 0.32
120
+ 2023-10-18 18:54:02,934 saving best model
121
+ 2023-10-18 18:54:02,977 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 18:54:04,826 epoch 4 - iter 73/738 - loss 0.36944310 - time (sec): 1.85 - samples/sec: 9510.06 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 18:54:06,476 epoch 4 - iter 146/738 - loss 0.35416470 - time (sec): 3.50 - samples/sec: 9315.70 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-18 18:54:08,180 epoch 4 - iter 219/738 - loss 0.36472416 - time (sec): 5.20 - samples/sec: 9343.76 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 18:54:09,909 epoch 4 - iter 292/738 - loss 0.36539814 - time (sec): 6.93 - samples/sec: 9519.65 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 18:54:11,751 epoch 4 - iter 365/738 - loss 0.36058865 - time (sec): 8.77 - samples/sec: 9569.18 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-18 18:54:13,564 epoch 4 - iter 438/738 - loss 0.36988378 - time (sec): 10.59 - samples/sec: 9494.32 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 18:54:15,301 epoch 4 - iter 511/738 - loss 0.36884095 - time (sec): 12.32 - samples/sec: 9483.53 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 18:54:16,957 epoch 4 - iter 584/738 - loss 0.36969941 - time (sec): 13.98 - samples/sec: 9494.13 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-18 18:54:18,684 epoch 4 - iter 657/738 - loss 0.36761614 - time (sec): 15.71 - samples/sec: 9486.58 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 18:54:20,383 epoch 4 - iter 730/738 - loss 0.36714089 - time (sec): 17.40 - samples/sec: 9473.64 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-18 18:54:20,563 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 18:54:20,563 EPOCH 4 done: loss 0.3663 - lr: 0.000020
134
+ 2023-10-18 18:54:27,702 DEV : loss 0.2950303554534912 - f1-score (micro avg) 0.3587
135
+ 2023-10-18 18:54:27,728 saving best model
136
+ 2023-10-18 18:54:27,766 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 18:54:29,457 epoch 5 - iter 73/738 - loss 0.34146707 - time (sec): 1.69 - samples/sec: 9529.99 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-18 18:54:31,179 epoch 5 - iter 146/738 - loss 0.34642612 - time (sec): 3.41 - samples/sec: 9364.92 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 18:54:32,907 epoch 5 - iter 219/738 - loss 0.34668670 - time (sec): 5.14 - samples/sec: 9395.92 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 18:54:35,219 epoch 5 - iter 292/738 - loss 0.34194245 - time (sec): 7.45 - samples/sec: 9100.75 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-18 18:54:37,017 epoch 5 - iter 365/738 - loss 0.34187389 - time (sec): 9.25 - samples/sec: 9123.73 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 18:54:38,755 epoch 5 - iter 438/738 - loss 0.34124463 - time (sec): 10.99 - samples/sec: 9147.79 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 18:54:40,488 epoch 5 - iter 511/738 - loss 0.34019308 - time (sec): 12.72 - samples/sec: 8986.48 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-18 18:54:42,281 epoch 5 - iter 584/738 - loss 0.34038501 - time (sec): 14.51 - samples/sec: 8887.32 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 18:54:44,097 epoch 5 - iter 657/738 - loss 0.33829006 - time (sec): 16.33 - samples/sec: 8947.38 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 18:54:45,929 epoch 5 - iter 730/738 - loss 0.33961410 - time (sec): 18.16 - samples/sec: 9066.69 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-18 18:54:46,122 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 18:54:46,122 EPOCH 5 done: loss 0.3400 - lr: 0.000017
149
+ 2023-10-18 18:54:53,313 DEV : loss 0.2756083011627197 - f1-score (micro avg) 0.3862
150
+ 2023-10-18 18:54:53,339 saving best model
151
+ 2023-10-18 18:54:53,378 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 18:54:55,141 epoch 6 - iter 73/738 - loss 0.34120287 - time (sec): 1.76 - samples/sec: 10190.28 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 18:54:56,920 epoch 6 - iter 146/738 - loss 0.32162573 - time (sec): 3.54 - samples/sec: 9838.24 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-18 18:54:58,625 epoch 6 - iter 219/738 - loss 0.31874927 - time (sec): 5.25 - samples/sec: 9710.50 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-18 18:55:00,318 epoch 6 - iter 292/738 - loss 0.32065056 - time (sec): 6.94 - samples/sec: 9693.25 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 18:55:02,163 epoch 6 - iter 365/738 - loss 0.31480678 - time (sec): 8.78 - samples/sec: 9569.85 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-18 18:55:03,941 epoch 6 - iter 438/738 - loss 0.32409156 - time (sec): 10.56 - samples/sec: 9331.67 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-18 18:55:05,700 epoch 6 - iter 511/738 - loss 0.32737315 - time (sec): 12.32 - samples/sec: 9351.69 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 18:55:07,401 epoch 6 - iter 584/738 - loss 0.32330551 - time (sec): 14.02 - samples/sec: 9309.21 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-18 18:55:09,120 epoch 6 - iter 657/738 - loss 0.32258843 - time (sec): 15.74 - samples/sec: 9300.41 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-18 18:55:10,901 epoch 6 - iter 730/738 - loss 0.32208614 - time (sec): 17.52 - samples/sec: 9395.06 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-18 18:55:11,098 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 18:55:11,098 EPOCH 6 done: loss 0.3219 - lr: 0.000013
164
+ 2023-10-18 18:55:18,261 DEV : loss 0.26639610528945923 - f1-score (micro avg) 0.4146
165
+ 2023-10-18 18:55:18,288 saving best model
166
+ 2023-10-18 18:55:18,322 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 18:55:20,066 epoch 7 - iter 73/738 - loss 0.30556597 - time (sec): 1.74 - samples/sec: 9564.01 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-18 18:55:21,775 epoch 7 - iter 146/738 - loss 0.31726978 - time (sec): 3.45 - samples/sec: 9546.50 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-18 18:55:23,473 epoch 7 - iter 219/738 - loss 0.30091048 - time (sec): 5.15 - samples/sec: 9444.26 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 18:55:25,177 epoch 7 - iter 292/738 - loss 0.30981691 - time (sec): 6.85 - samples/sec: 9502.79 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-18 18:55:26,970 epoch 7 - iter 365/738 - loss 0.30604870 - time (sec): 8.65 - samples/sec: 9520.74 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-18 18:55:28,704 epoch 7 - iter 438/738 - loss 0.30386617 - time (sec): 10.38 - samples/sec: 9526.86 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 18:55:30,392 epoch 7 - iter 511/738 - loss 0.30690882 - time (sec): 12.07 - samples/sec: 9522.71 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-18 18:55:32,166 epoch 7 - iter 584/738 - loss 0.30363679 - time (sec): 13.84 - samples/sec: 9488.93 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-18 18:55:33,875 epoch 7 - iter 657/738 - loss 0.30303827 - time (sec): 15.55 - samples/sec: 9521.30 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-18 18:55:35,616 epoch 7 - iter 730/738 - loss 0.30566278 - time (sec): 17.29 - samples/sec: 9534.15 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-18 18:55:35,806 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 18:55:35,806 EPOCH 7 done: loss 0.3074 - lr: 0.000010
179
+ 2023-10-18 18:55:42,992 DEV : loss 0.2636333405971527 - f1-score (micro avg) 0.4126
180
+ 2023-10-18 18:55:43,019 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-18 18:55:44,858 epoch 8 - iter 73/738 - loss 0.30261683 - time (sec): 1.84 - samples/sec: 11006.58 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-18 18:55:46,596 epoch 8 - iter 146/738 - loss 0.30342876 - time (sec): 3.58 - samples/sec: 10365.01 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-18 18:55:48,328 epoch 8 - iter 219/738 - loss 0.29957239 - time (sec): 5.31 - samples/sec: 9959.68 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-18 18:55:50,041 epoch 8 - iter 292/738 - loss 0.30420435 - time (sec): 7.02 - samples/sec: 9882.01 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-18 18:55:51,706 epoch 8 - iter 365/738 - loss 0.29943806 - time (sec): 8.69 - samples/sec: 9704.42 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-18 18:55:53,371 epoch 8 - iter 438/738 - loss 0.30018714 - time (sec): 10.35 - samples/sec: 9670.71 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-18 18:55:55,084 epoch 8 - iter 511/738 - loss 0.29946570 - time (sec): 12.06 - samples/sec: 9639.16 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-18 18:55:56,861 epoch 8 - iter 584/738 - loss 0.29967547 - time (sec): 13.84 - samples/sec: 9609.30 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-18 18:55:58,534 epoch 8 - iter 657/738 - loss 0.30042341 - time (sec): 15.51 - samples/sec: 9584.72 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-18 18:56:00,204 epoch 8 - iter 730/738 - loss 0.29829974 - time (sec): 17.18 - samples/sec: 9567.93 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-18 18:56:00,391 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-18 18:56:00,391 EPOCH 8 done: loss 0.2999 - lr: 0.000007
193
+ 2023-10-18 18:56:07,599 DEV : loss 0.2585228383541107 - f1-score (micro avg) 0.4277
194
+ 2023-10-18 18:56:07,625 saving best model
195
+ 2023-10-18 18:56:07,658 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-18 18:56:09,344 epoch 9 - iter 73/738 - loss 0.30758024 - time (sec): 1.69 - samples/sec: 9099.32 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-18 18:56:11,067 epoch 9 - iter 146/738 - loss 0.28960177 - time (sec): 3.41 - samples/sec: 9174.55 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-18 18:56:12,916 epoch 9 - iter 219/738 - loss 0.30272308 - time (sec): 5.26 - samples/sec: 9519.35 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-18 18:56:15,107 epoch 9 - iter 292/738 - loss 0.30045146 - time (sec): 7.45 - samples/sec: 8945.26 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-18 18:56:16,846 epoch 9 - iter 365/738 - loss 0.30003631 - time (sec): 9.19 - samples/sec: 8958.35 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-18 18:56:18,557 epoch 9 - iter 438/738 - loss 0.30160690 - time (sec): 10.90 - samples/sec: 8970.13 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-18 18:56:20,297 epoch 9 - iter 511/738 - loss 0.29885683 - time (sec): 12.64 - samples/sec: 9090.97 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-18 18:56:22,022 epoch 9 - iter 584/738 - loss 0.29861281 - time (sec): 14.36 - samples/sec: 9134.26 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-18 18:56:23,671 epoch 9 - iter 657/738 - loss 0.29753874 - time (sec): 16.01 - samples/sec: 9118.57 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-18 18:56:25,423 epoch 9 - iter 730/738 - loss 0.29722536 - time (sec): 17.76 - samples/sec: 9159.83 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-18 18:56:25,709 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-18 18:56:25,709 EPOCH 9 done: loss 0.2950 - lr: 0.000003
208
+ 2023-10-18 18:56:32,950 DEV : loss 0.2576240301132202 - f1-score (micro avg) 0.431
209
+ 2023-10-18 18:56:32,976 saving best model
210
+ 2023-10-18 18:56:33,008 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-18 18:56:34,836 epoch 10 - iter 73/738 - loss 0.25004751 - time (sec): 1.83 - samples/sec: 9649.60 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-18 18:56:36,574 epoch 10 - iter 146/738 - loss 0.26018308 - time (sec): 3.57 - samples/sec: 9518.95 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-18 18:56:38,376 epoch 10 - iter 219/738 - loss 0.27025184 - time (sec): 5.37 - samples/sec: 9358.69 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-18 18:56:40,175 epoch 10 - iter 292/738 - loss 0.27857312 - time (sec): 7.17 - samples/sec: 9197.61 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-18 18:56:41,871 epoch 10 - iter 365/738 - loss 0.28303110 - time (sec): 8.86 - samples/sec: 9296.23 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-18 18:56:43,610 epoch 10 - iter 438/738 - loss 0.28434751 - time (sec): 10.60 - samples/sec: 9421.95 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 18:56:45,319 epoch 10 - iter 511/738 - loss 0.28539794 - time (sec): 12.31 - samples/sec: 9386.12 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 18:56:47,129 epoch 10 - iter 584/738 - loss 0.28911825 - time (sec): 14.12 - samples/sec: 9443.73 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 18:56:48,852 epoch 10 - iter 657/738 - loss 0.28832023 - time (sec): 15.84 - samples/sec: 9435.15 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 18:56:50,534 epoch 10 - iter 730/738 - loss 0.28826766 - time (sec): 17.52 - samples/sec: 9417.66 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-18 18:56:50,717 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-18 18:56:50,718 EPOCH 10 done: loss 0.2885 - lr: 0.000000
223
+ 2023-10-18 18:56:57,957 DEV : loss 0.2570817172527313 - f1-score (micro avg) 0.4335
224
+ 2023-10-18 18:56:57,984 saving best model
225
+ 2023-10-18 18:56:58,046 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-18 18:56:58,046 Loading model from best epoch ...
227
+ 2023-10-18 18:56:58,126 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
228
+ 2023-10-18 18:57:00,796
229
+ Results:
230
+ - F-score (micro) 0.4619
231
+ - F-score (macro) 0.2331
232
+ - Accuracy 0.3203
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ loc 0.4967 0.6935 0.5788 858
238
+ pers 0.3154 0.4246 0.3619 537
239
+ org 0.1429 0.0076 0.0144 132
240
+ time 0.2439 0.1852 0.2105 54
241
+ prod 0.0000 0.0000 0.0000 61
242
+
243
+ micro avg 0.4236 0.5079 0.4619 1642
244
+ macro avg 0.2398 0.2622 0.2331 1642
245
+ weighted avg 0.3822 0.5079 0.4289 1642
246
+
247
+ 2023-10-18 18:57:00,796 ----------------------------------------------------------------------------------------------------