Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmbert_tiny-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
78d1470
•
1 Parent(s): 46dbbcd

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.1697676908.46dc0c540dd0.3802.10 +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 sha256:05fee56dbf242e3a673e290f801247fb6612a1f615341d0e754d11cce259f22c
3
+ size 19045922
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 00:55:52 0.0000 0.8204 0.1883 0.2218 0.0652 0.1008 0.0539
3
+ 2 00:56:39 0.0000 0.1987 0.1625 0.2964 0.3730 0.3303 0.2072
4
+ 3 00:57:25 0.0000 0.1650 0.1545 0.3808 0.3490 0.3642 0.2293
5
+ 4 00:58:11 0.0000 0.1497 0.1540 0.3642 0.4680 0.4096 0.2680
6
+ 5 00:58:58 0.0000 0.1376 0.1569 0.3755 0.5092 0.4322 0.2860
7
+ 6 00:59:44 0.0000 0.1319 0.1584 0.3862 0.5240 0.4447 0.2976
8
+ 7 01:00:30 0.0000 0.1249 0.1555 0.3968 0.5080 0.4456 0.2962
9
+ 8 01:01:16 0.0000 0.1192 0.1602 0.3990 0.5378 0.4581 0.3080
10
+ 9 01:02:02 0.0000 0.1172 0.1613 0.3961 0.5629 0.4650 0.3144
11
+ 10 01:02:48 0.0000 0.1165 0.1602 0.3993 0.5584 0.4656 0.3148
runs/events.out.tfevents.1697676908.46dc0c540dd0.3802.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0943e6e9cd795f76fbabdaa97ba10ad688a6c6c8ef5b007566f5fe6302e32f52
3
+ size 1018100
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-19 00:55:08,399 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 00:55:08,399 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=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-19 00:55:08,399 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 00:55:08,399 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
52
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
53
+ 2023-10-19 00:55:08,399 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-19 00:55:08,399 Train: 14465 sentences
55
+ 2023-10-19 00:55:08,399 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-19 00:55:08,399 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-19 00:55:08,399 Training Params:
58
+ 2023-10-19 00:55:08,399 - learning_rate: "3e-05"
59
+ 2023-10-19 00:55:08,399 - mini_batch_size: "8"
60
+ 2023-10-19 00:55:08,400 - max_epochs: "10"
61
+ 2023-10-19 00:55:08,400 - shuffle: "True"
62
+ 2023-10-19 00:55:08,400 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-19 00:55:08,400 Plugins:
64
+ 2023-10-19 00:55:08,400 - TensorboardLogger
65
+ 2023-10-19 00:55:08,400 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-19 00:55:08,400 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-19 00:55:08,400 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-19 00:55:08,400 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-19 00:55:08,400 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-19 00:55:08,400 Computation:
71
+ 2023-10-19 00:55:08,400 - compute on device: cuda:0
72
+ 2023-10-19 00:55:08,400 - embedding storage: none
73
+ 2023-10-19 00:55:08,400 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-19 00:55:08,400 Model training base path: "hmbench-letemps/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-19 00:55:08,400 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 00:55:08,400 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-19 00:55:08,400 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-19 00:55:12,651 epoch 1 - iter 180/1809 - loss 3.02059904 - time (sec): 4.25 - samples/sec: 9147.25 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-19 00:55:16,860 epoch 1 - iter 360/1809 - loss 2.59240564 - time (sec): 8.46 - samples/sec: 8968.75 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-19 00:55:21,151 epoch 1 - iter 540/1809 - loss 2.03891534 - time (sec): 12.75 - samples/sec: 8948.76 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-19 00:55:25,390 epoch 1 - iter 720/1809 - loss 1.63251111 - time (sec): 16.99 - samples/sec: 8927.94 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-19 00:55:29,608 epoch 1 - iter 900/1809 - loss 1.36226435 - time (sec): 21.21 - samples/sec: 9018.73 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-19 00:55:33,791 epoch 1 - iter 1080/1809 - loss 1.18357407 - time (sec): 25.39 - samples/sec: 9057.79 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-19 00:55:37,901 epoch 1 - iter 1260/1809 - loss 1.06438656 - time (sec): 29.50 - samples/sec: 9006.09 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-19 00:55:42,120 epoch 1 - iter 1440/1809 - loss 0.96650038 - time (sec): 33.72 - samples/sec: 8998.06 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-19 00:55:46,289 epoch 1 - iter 1620/1809 - loss 0.88699189 - time (sec): 37.89 - samples/sec: 8986.47 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-19 00:55:50,495 epoch 1 - iter 1800/1809 - loss 0.82250609 - time (sec): 42.10 - samples/sec: 8995.27 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-19 00:55:50,684 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-19 00:55:50,684 EPOCH 1 done: loss 0.8204 - lr: 0.000030
90
+ 2023-10-19 00:55:52,944 DEV : loss 0.18831811845302582 - f1-score (micro avg) 0.1008
91
+ 2023-10-19 00:55:52,971 saving best model
92
+ 2023-10-19 00:55:53,001 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-19 00:55:57,197 epoch 2 - iter 180/1809 - loss 0.23379582 - time (sec): 4.20 - samples/sec: 8960.12 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-19 00:56:01,382 epoch 2 - iter 360/1809 - loss 0.22598926 - time (sec): 8.38 - samples/sec: 9041.69 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-19 00:56:06,265 epoch 2 - iter 540/1809 - loss 0.21606913 - time (sec): 13.26 - samples/sec: 8611.22 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-19 00:56:10,362 epoch 2 - iter 720/1809 - loss 0.21128402 - time (sec): 17.36 - samples/sec: 8626.96 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-19 00:56:14,495 epoch 2 - iter 900/1809 - loss 0.20916640 - time (sec): 21.49 - samples/sec: 8655.64 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-19 00:56:18,779 epoch 2 - iter 1080/1809 - loss 0.20755304 - time (sec): 25.78 - samples/sec: 8741.45 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-19 00:56:22,933 epoch 2 - iter 1260/1809 - loss 0.20505981 - time (sec): 29.93 - samples/sec: 8787.58 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-19 00:56:27,097 epoch 2 - iter 1440/1809 - loss 0.20371547 - time (sec): 34.10 - samples/sec: 8800.24 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-19 00:56:31,349 epoch 2 - iter 1620/1809 - loss 0.20010663 - time (sec): 38.35 - samples/sec: 8831.85 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-19 00:56:35,594 epoch 2 - iter 1800/1809 - loss 0.19871096 - time (sec): 42.59 - samples/sec: 8875.93 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-19 00:56:35,803 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-19 00:56:35,803 EPOCH 2 done: loss 0.1987 - lr: 0.000027
105
+ 2023-10-19 00:56:38,999 DEV : loss 0.1624661087989807 - f1-score (micro avg) 0.3303
106
+ 2023-10-19 00:56:39,026 saving best model
107
+ 2023-10-19 00:56:39,058 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-19 00:56:43,380 epoch 3 - iter 180/1809 - loss 0.16077504 - time (sec): 4.32 - samples/sec: 8719.75 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-19 00:56:47,669 epoch 3 - iter 360/1809 - loss 0.16133266 - time (sec): 8.61 - samples/sec: 8780.24 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-19 00:56:52,002 epoch 3 - iter 540/1809 - loss 0.16796854 - time (sec): 12.94 - samples/sec: 8782.24 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-19 00:56:56,217 epoch 3 - iter 720/1809 - loss 0.17031261 - time (sec): 17.16 - samples/sec: 8823.88 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-19 00:57:00,632 epoch 3 - iter 900/1809 - loss 0.16734894 - time (sec): 21.57 - samples/sec: 8814.43 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-19 00:57:04,969 epoch 3 - iter 1080/1809 - loss 0.16844113 - time (sec): 25.91 - samples/sec: 8772.84 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-19 00:57:09,257 epoch 3 - iter 1260/1809 - loss 0.16814282 - time (sec): 30.20 - samples/sec: 8801.78 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-19 00:57:13,430 epoch 3 - iter 1440/1809 - loss 0.16710162 - time (sec): 34.37 - samples/sec: 8831.62 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-19 00:57:17,630 epoch 3 - iter 1620/1809 - loss 0.16523955 - time (sec): 38.57 - samples/sec: 8838.63 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-19 00:57:21,905 epoch 3 - iter 1800/1809 - loss 0.16521378 - time (sec): 42.85 - samples/sec: 8826.30 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-19 00:57:22,108 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-19 00:57:22,108 EPOCH 3 done: loss 0.1650 - lr: 0.000023
120
+ 2023-10-19 00:57:25,860 DEV : loss 0.1545405089855194 - f1-score (micro avg) 0.3642
121
+ 2023-10-19 00:57:25,887 saving best model
122
+ 2023-10-19 00:57:25,925 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-19 00:57:30,131 epoch 4 - iter 180/1809 - loss 0.15355927 - time (sec): 4.21 - samples/sec: 8784.05 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-19 00:57:34,395 epoch 4 - iter 360/1809 - loss 0.15216298 - time (sec): 8.47 - samples/sec: 8948.25 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-19 00:57:38,701 epoch 4 - iter 540/1809 - loss 0.15726329 - time (sec): 12.78 - samples/sec: 8876.64 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-19 00:57:42,969 epoch 4 - iter 720/1809 - loss 0.15406047 - time (sec): 17.04 - samples/sec: 8893.59 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-19 00:57:47,289 epoch 4 - iter 900/1809 - loss 0.15371008 - time (sec): 21.36 - samples/sec: 8883.62 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-19 00:57:51,506 epoch 4 - iter 1080/1809 - loss 0.15297029 - time (sec): 25.58 - samples/sec: 8871.45 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-19 00:57:55,625 epoch 4 - iter 1260/1809 - loss 0.15162532 - time (sec): 29.70 - samples/sec: 8847.34 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-19 00:57:59,903 epoch 4 - iter 1440/1809 - loss 0.15023300 - time (sec): 33.98 - samples/sec: 8887.31 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-19 00:58:04,111 epoch 4 - iter 1620/1809 - loss 0.14985131 - time (sec): 38.19 - samples/sec: 8936.38 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-19 00:58:08,343 epoch 4 - iter 1800/1809 - loss 0.14967964 - time (sec): 42.42 - samples/sec: 8912.53 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-19 00:58:08,544 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-19 00:58:08,544 EPOCH 4 done: loss 0.1497 - lr: 0.000020
135
+ 2023-10-19 00:58:11,752 DEV : loss 0.15396162867546082 - f1-score (micro avg) 0.4096
136
+ 2023-10-19 00:58:11,781 saving best model
137
+ 2023-10-19 00:58:11,817 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-19 00:58:16,031 epoch 5 - iter 180/1809 - loss 0.15330329 - time (sec): 4.21 - samples/sec: 8377.02 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-19 00:58:20,408 epoch 5 - iter 360/1809 - loss 0.14613552 - time (sec): 8.59 - samples/sec: 8656.53 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-19 00:58:24,697 epoch 5 - iter 540/1809 - loss 0.13629708 - time (sec): 12.88 - samples/sec: 8629.68 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-19 00:58:29,017 epoch 5 - iter 720/1809 - loss 0.13634111 - time (sec): 17.20 - samples/sec: 8693.16 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-19 00:58:33,228 epoch 5 - iter 900/1809 - loss 0.13677079 - time (sec): 21.41 - samples/sec: 8693.05 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-19 00:58:37,395 epoch 5 - iter 1080/1809 - loss 0.13705700 - time (sec): 25.58 - samples/sec: 8799.68 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-19 00:58:41,676 epoch 5 - iter 1260/1809 - loss 0.13678143 - time (sec): 29.86 - samples/sec: 8871.29 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-19 00:58:45,897 epoch 5 - iter 1440/1809 - loss 0.13770878 - time (sec): 34.08 - samples/sec: 8873.33 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-19 00:58:50,129 epoch 5 - iter 1620/1809 - loss 0.13719641 - time (sec): 38.31 - samples/sec: 8900.11 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-19 00:58:54,302 epoch 5 - iter 1800/1809 - loss 0.13755607 - time (sec): 42.48 - samples/sec: 8901.51 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-19 00:58:54,513 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-19 00:58:54,513 EPOCH 5 done: loss 0.1376 - lr: 0.000017
150
+ 2023-10-19 00:58:58,318 DEV : loss 0.15693862736225128 - f1-score (micro avg) 0.4322
151
+ 2023-10-19 00:58:58,347 saving best model
152
+ 2023-10-19 00:58:58,387 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-19 00:59:02,681 epoch 6 - iter 180/1809 - loss 0.12354942 - time (sec): 4.29 - samples/sec: 8938.29 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-19 00:59:06,923 epoch 6 - iter 360/1809 - loss 0.12329277 - time (sec): 8.54 - samples/sec: 8790.19 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-19 00:59:11,152 epoch 6 - iter 540/1809 - loss 0.12382227 - time (sec): 12.76 - samples/sec: 8880.49 - lr: 0.000016 - momentum: 0.000000
156
+ 2023-10-19 00:59:15,382 epoch 6 - iter 720/1809 - loss 0.12812576 - time (sec): 16.99 - samples/sec: 8824.66 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-19 00:59:19,569 epoch 6 - iter 900/1809 - loss 0.12995777 - time (sec): 21.18 - samples/sec: 8882.48 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-19 00:59:23,761 epoch 6 - iter 1080/1809 - loss 0.13162934 - time (sec): 25.37 - samples/sec: 8897.00 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-19 00:59:28,006 epoch 6 - iter 1260/1809 - loss 0.13296655 - time (sec): 29.62 - samples/sec: 8933.26 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-19 00:59:32,166 epoch 6 - iter 1440/1809 - loss 0.13302667 - time (sec): 33.78 - samples/sec: 8916.02 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-19 00:59:36,493 epoch 6 - iter 1620/1809 - loss 0.13312201 - time (sec): 38.11 - samples/sec: 8905.70 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-19 00:59:40,713 epoch 6 - iter 1800/1809 - loss 0.13199896 - time (sec): 42.33 - samples/sec: 8919.97 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-19 00:59:40,938 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-19 00:59:40,938 EPOCH 6 done: loss 0.1319 - lr: 0.000013
165
+ 2023-10-19 00:59:44,140 DEV : loss 0.15839844942092896 - f1-score (micro avg) 0.4447
166
+ 2023-10-19 00:59:44,170 saving best model
167
+ 2023-10-19 00:59:44,208 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-19 00:59:48,386 epoch 7 - iter 180/1809 - loss 0.12883141 - time (sec): 4.18 - samples/sec: 9157.87 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-19 00:59:52,409 epoch 7 - iter 360/1809 - loss 0.12400669 - time (sec): 8.20 - samples/sec: 9283.73 - lr: 0.000013 - momentum: 0.000000
170
+ 2023-10-19 00:59:56,667 epoch 7 - iter 540/1809 - loss 0.12259146 - time (sec): 12.46 - samples/sec: 9152.68 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-19 01:00:00,980 epoch 7 - iter 720/1809 - loss 0.12350739 - time (sec): 16.77 - samples/sec: 9051.03 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-19 01:00:05,186 epoch 7 - iter 900/1809 - loss 0.12312114 - time (sec): 20.98 - samples/sec: 9025.80 - lr: 0.000012 - momentum: 0.000000
173
+ 2023-10-19 01:00:09,488 epoch 7 - iter 1080/1809 - loss 0.12684864 - time (sec): 25.28 - samples/sec: 8956.39 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-19 01:00:13,954 epoch 7 - iter 1260/1809 - loss 0.12759953 - time (sec): 29.74 - samples/sec: 8905.46 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-19 01:00:18,107 epoch 7 - iter 1440/1809 - loss 0.12647126 - time (sec): 33.90 - samples/sec: 8894.61 - lr: 0.000011 - momentum: 0.000000
176
+ 2023-10-19 01:00:22,429 epoch 7 - iter 1620/1809 - loss 0.12603946 - time (sec): 38.22 - samples/sec: 8877.74 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-19 01:00:26,698 epoch 7 - iter 1800/1809 - loss 0.12487945 - time (sec): 42.49 - samples/sec: 8893.36 - lr: 0.000010 - momentum: 0.000000
178
+ 2023-10-19 01:00:26,911 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-19 01:00:26,911 EPOCH 7 done: loss 0.1249 - lr: 0.000010
180
+ 2023-10-19 01:00:30,696 DEV : loss 0.15553328394889832 - f1-score (micro avg) 0.4456
181
+ 2023-10-19 01:00:30,724 saving best model
182
+ 2023-10-19 01:00:30,757 ----------------------------------------------------------------------------------------------------
183
+ 2023-10-19 01:00:35,031 epoch 8 - iter 180/1809 - loss 0.11513408 - time (sec): 4.27 - samples/sec: 9108.93 - lr: 0.000010 - momentum: 0.000000
184
+ 2023-10-19 01:00:39,276 epoch 8 - iter 360/1809 - loss 0.11403661 - time (sec): 8.52 - samples/sec: 9164.60 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-19 01:00:43,549 epoch 8 - iter 540/1809 - loss 0.11605998 - time (sec): 12.79 - samples/sec: 9073.43 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-19 01:00:47,776 epoch 8 - iter 720/1809 - loss 0.11460389 - time (sec): 17.02 - samples/sec: 9048.75 - lr: 0.000009 - momentum: 0.000000
187
+ 2023-10-19 01:00:52,038 epoch 8 - iter 900/1809 - loss 0.11892077 - time (sec): 21.28 - samples/sec: 9056.00 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-19 01:00:56,269 epoch 8 - iter 1080/1809 - loss 0.11833919 - time (sec): 25.51 - samples/sec: 9032.48 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-19 01:01:00,443 epoch 8 - iter 1260/1809 - loss 0.11862510 - time (sec): 29.68 - samples/sec: 9007.98 - lr: 0.000008 - momentum: 0.000000
190
+ 2023-10-19 01:01:04,678 epoch 8 - iter 1440/1809 - loss 0.11840134 - time (sec): 33.92 - samples/sec: 8974.47 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-19 01:01:08,829 epoch 8 - iter 1620/1809 - loss 0.11883557 - time (sec): 38.07 - samples/sec: 8985.37 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-19 01:01:13,012 epoch 8 - iter 1800/1809 - loss 0.11942175 - time (sec): 42.25 - samples/sec: 8943.81 - lr: 0.000007 - momentum: 0.000000
193
+ 2023-10-19 01:01:13,228 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-19 01:01:13,228 EPOCH 8 done: loss 0.1192 - lr: 0.000007
195
+ 2023-10-19 01:01:16,438 DEV : loss 0.16024847328662872 - f1-score (micro avg) 0.4581
196
+ 2023-10-19 01:01:16,466 saving best model
197
+ 2023-10-19 01:01:16,497 ----------------------------------------------------------------------------------------------------
198
+ 2023-10-19 01:01:20,726 epoch 9 - iter 180/1809 - loss 0.11259705 - time (sec): 4.23 - samples/sec: 9054.25 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-19 01:01:24,835 epoch 9 - iter 360/1809 - loss 0.11599603 - time (sec): 8.34 - samples/sec: 9031.02 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-19 01:01:29,005 epoch 9 - iter 540/1809 - loss 0.11430380 - time (sec): 12.51 - samples/sec: 9048.96 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-19 01:01:33,297 epoch 9 - iter 720/1809 - loss 0.11420665 - time (sec): 16.80 - samples/sec: 8952.07 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-19 01:01:37,154 epoch 9 - iter 900/1809 - loss 0.11560138 - time (sec): 20.66 - samples/sec: 9153.90 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-19 01:01:41,366 epoch 9 - iter 1080/1809 - loss 0.11787546 - time (sec): 24.87 - samples/sec: 9093.09 - lr: 0.000005 - momentum: 0.000000
204
+ 2023-10-19 01:01:45,609 epoch 9 - iter 1260/1809 - loss 0.11693200 - time (sec): 29.11 - samples/sec: 9069.64 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-19 01:01:49,850 epoch 9 - iter 1440/1809 - loss 0.11685936 - time (sec): 33.35 - samples/sec: 9041.80 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-19 01:01:54,173 epoch 9 - iter 1620/1809 - loss 0.11583111 - time (sec): 37.68 - samples/sec: 8987.30 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-19 01:01:58,485 epoch 9 - iter 1800/1809 - loss 0.11702665 - time (sec): 41.99 - samples/sec: 9014.85 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-19 01:01:58,686 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-19 01:01:58,686 EPOCH 9 done: loss 0.1172 - lr: 0.000003
210
+ 2023-10-19 01:02:02,531 DEV : loss 0.16129888594150543 - f1-score (micro avg) 0.465
211
+ 2023-10-19 01:02:02,559 saving best model
212
+ 2023-10-19 01:02:02,596 ----------------------------------------------------------------------------------------------------
213
+ 2023-10-19 01:02:06,956 epoch 10 - iter 180/1809 - loss 0.11628266 - time (sec): 4.36 - samples/sec: 8815.42 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-19 01:02:11,145 epoch 10 - iter 360/1809 - loss 0.11391073 - time (sec): 8.55 - samples/sec: 8972.40 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-19 01:02:15,290 epoch 10 - iter 540/1809 - loss 0.12021392 - time (sec): 12.69 - samples/sec: 8842.68 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-19 01:02:19,563 epoch 10 - iter 720/1809 - loss 0.11652333 - time (sec): 16.97 - samples/sec: 8884.38 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-19 01:02:23,789 epoch 10 - iter 900/1809 - loss 0.11604266 - time (sec): 21.19 - samples/sec: 8932.15 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-19 01:02:28,092 epoch 10 - iter 1080/1809 - loss 0.11441938 - time (sec): 25.50 - samples/sec: 8944.45 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-19 01:02:32,319 epoch 10 - iter 1260/1809 - loss 0.11448108 - time (sec): 29.72 - samples/sec: 8913.31 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-19 01:02:36,556 epoch 10 - iter 1440/1809 - loss 0.11365218 - time (sec): 33.96 - samples/sec: 8955.55 - lr: 0.000001 - momentum: 0.000000
221
+ 2023-10-19 01:02:40,682 epoch 10 - iter 1620/1809 - loss 0.11589731 - time (sec): 38.09 - samples/sec: 8991.07 - lr: 0.000000 - momentum: 0.000000
222
+ 2023-10-19 01:02:44,829 epoch 10 - iter 1800/1809 - loss 0.11657828 - time (sec): 42.23 - samples/sec: 8950.50 - lr: 0.000000 - momentum: 0.000000
223
+ 2023-10-19 01:02:45,039 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-19 01:02:45,039 EPOCH 10 done: loss 0.1165 - lr: 0.000000
225
+ 2023-10-19 01:02:48,223 DEV : loss 0.1601785123348236 - f1-score (micro avg) 0.4656
226
+ 2023-10-19 01:02:48,251 saving best model
227
+ 2023-10-19 01:02:48,313 ----------------------------------------------------------------------------------------------------
228
+ 2023-10-19 01:02:48,313 Loading model from best epoch ...
229
+ 2023-10-19 01:02:48,391 SequenceTagger predicts: Dictionary with 13 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
230
+ 2023-10-19 01:02:52,385
231
+ Results:
232
+ - F-score (micro) 0.4939
233
+ - F-score (macro) 0.3255
234
+ - Accuracy 0.3406
235
+
236
+ By class:
237
+ precision recall f1-score support
238
+
239
+ loc 0.5032 0.6650 0.5729 591
240
+ pers 0.3771 0.4342 0.4036 357
241
+ org 0.0000 0.0000 0.0000 79
242
+
243
+ micro avg 0.4597 0.5336 0.4939 1027
244
+ macro avg 0.2934 0.3664 0.3255 1027
245
+ weighted avg 0.4207 0.5336 0.4700 1027
246
+
247
+ 2023-10-19 01:02:52,386 ----------------------------------------------------------------------------------------------------