Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmbert-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
aa2412e
·
1 Parent(s): 098602a

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +241 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7ba022cd3eb75d155cc9c5888be90da571447d579f29b938ad016827443edd
3
+ size 443311111
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 19:08:04 0.0000 0.2432 0.1393 0.5138 0.6373 0.5689 0.4051
3
+ 2 19:10:55 0.0000 0.1044 0.1309 0.5604 0.6796 0.6143 0.4500
4
+ 3 19:13:46 0.0000 0.0815 0.1881 0.5478 0.7403 0.6297 0.4716
5
+ 4 19:16:35 0.0000 0.0614 0.2195 0.5530 0.7048 0.6197 0.4563
6
+ 5 19:19:25 0.0000 0.0443 0.3202 0.5204 0.7723 0.6218 0.4601
7
+ 6 19:22:13 0.0000 0.0340 0.2958 0.5513 0.7494 0.6353 0.4743
8
+ 7 19:25:04 0.0000 0.0237 0.2668 0.5551 0.7551 0.6398 0.4793
9
+ 8 19:27:54 0.0000 0.0153 0.3516 0.5464 0.7540 0.6337 0.4738
10
+ 9 19:30:45 0.0000 0.0098 0.3658 0.5435 0.7792 0.6403 0.4820
11
+ 10 19:33:35 0.0000 0.0061 0.3829 0.5407 0.7609 0.6321 0.4726
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-14 19:05:16,272 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-14 19:05:16,273 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
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): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
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): BertSelfOutput(
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): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
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
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-14 19:05:16,273 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-14 19:05:16,273 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
+ 2023-10-14 19:05:16,273 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-14 19:05:16,273 Train: 14465 sentences
55
+ 2023-10-14 19:05:16,273 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-14 19:05:16,273 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-14 19:05:16,273 Training Params:
58
+ 2023-10-14 19:05:16,273 - learning_rate: "5e-05"
59
+ 2023-10-14 19:05:16,273 - mini_batch_size: "4"
60
+ 2023-10-14 19:05:16,273 - max_epochs: "10"
61
+ 2023-10-14 19:05:16,273 - shuffle: "True"
62
+ 2023-10-14 19:05:16,273 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-14 19:05:16,273 Plugins:
64
+ 2023-10-14 19:05:16,273 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-14 19:05:16,273 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-14 19:05:16,273 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-14 19:05:16,274 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-14 19:05:16,274 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-14 19:05:16,281 Computation:
70
+ 2023-10-14 19:05:16,281 - compute on device: cuda:0
71
+ 2023-10-14 19:05:16,281 - embedding storage: none
72
+ 2023-10-14 19:05:16,281 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-14 19:05:16,281 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-14 19:05:16,281 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-14 19:05:16,281 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-14 19:05:32,627 epoch 1 - iter 361/3617 - loss 1.23920084 - time (sec): 16.34 - samples/sec: 2350.13 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-14 19:05:48,957 epoch 1 - iter 722/3617 - loss 0.71530722 - time (sec): 32.67 - samples/sec: 2334.39 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-14 19:06:05,427 epoch 1 - iter 1083/3617 - loss 0.53270967 - time (sec): 49.14 - samples/sec: 2315.81 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-14 19:06:22,334 epoch 1 - iter 1444/3617 - loss 0.42703208 - time (sec): 66.05 - samples/sec: 2316.46 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-14 19:06:38,623 epoch 1 - iter 1805/3617 - loss 0.36797501 - time (sec): 82.34 - samples/sec: 2312.38 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-14 19:06:54,895 epoch 1 - iter 2166/3617 - loss 0.32750828 - time (sec): 98.61 - samples/sec: 2310.32 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-14 19:07:11,180 epoch 1 - iter 2527/3617 - loss 0.29684754 - time (sec): 114.90 - samples/sec: 2307.26 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-14 19:07:27,493 epoch 1 - iter 2888/3617 - loss 0.27335721 - time (sec): 131.21 - samples/sec: 2323.15 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-14 19:07:43,729 epoch 1 - iter 3249/3617 - loss 0.25684398 - time (sec): 147.45 - samples/sec: 2318.20 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-14 19:08:00,221 epoch 1 - iter 3610/3617 - loss 0.24344102 - time (sec): 163.94 - samples/sec: 2313.29 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-14 19:08:00,523 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-14 19:08:00,523 EPOCH 1 done: loss 0.2432 - lr: 0.000050
88
+ 2023-10-14 19:08:04,935 DEV : loss 0.1392880529165268 - f1-score (micro avg) 0.5689
89
+ 2023-10-14 19:08:04,964 saving best model
90
+ 2023-10-14 19:08:05,441 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-14 19:08:22,439 epoch 2 - iter 361/3617 - loss 0.10163212 - time (sec): 17.00 - samples/sec: 2243.75 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-14 19:08:38,735 epoch 2 - iter 722/3617 - loss 0.10138989 - time (sec): 33.29 - samples/sec: 2294.93 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-14 19:08:55,123 epoch 2 - iter 1083/3617 - loss 0.10563254 - time (sec): 49.68 - samples/sec: 2312.87 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-14 19:09:11,321 epoch 2 - iter 1444/3617 - loss 0.10583746 - time (sec): 65.88 - samples/sec: 2308.77 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-14 19:09:28,181 epoch 2 - iter 1805/3617 - loss 0.10742122 - time (sec): 82.74 - samples/sec: 2285.53 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-14 19:09:44,590 epoch 2 - iter 2166/3617 - loss 0.10649535 - time (sec): 99.15 - samples/sec: 2297.31 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-14 19:10:00,921 epoch 2 - iter 2527/3617 - loss 0.10728153 - time (sec): 115.48 - samples/sec: 2303.87 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-14 19:10:17,234 epoch 2 - iter 2888/3617 - loss 0.10535240 - time (sec): 131.79 - samples/sec: 2303.35 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-14 19:10:33,540 epoch 2 - iter 3249/3617 - loss 0.10454269 - time (sec): 148.10 - samples/sec: 2307.34 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-14 19:10:49,774 epoch 2 - iter 3610/3617 - loss 0.10433026 - time (sec): 164.33 - samples/sec: 2307.84 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-14 19:10:50,080 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-14 19:10:50,080 EPOCH 2 done: loss 0.1044 - lr: 0.000044
103
+ 2023-10-14 19:10:55,595 DEV : loss 0.13085970282554626 - f1-score (micro avg) 0.6143
104
+ 2023-10-14 19:10:55,625 saving best model
105
+ 2023-10-14 19:10:56,106 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-14 19:11:12,432 epoch 3 - iter 361/3617 - loss 0.07918586 - time (sec): 16.32 - samples/sec: 2170.00 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-14 19:11:28,688 epoch 3 - iter 722/3617 - loss 0.07745191 - time (sec): 32.58 - samples/sec: 2257.80 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-14 19:11:44,987 epoch 3 - iter 1083/3617 - loss 0.07935488 - time (sec): 48.88 - samples/sec: 2279.45 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-14 19:12:01,266 epoch 3 - iter 1444/3617 - loss 0.08119260 - time (sec): 65.16 - samples/sec: 2314.24 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-14 19:12:17,499 epoch 3 - iter 1805/3617 - loss 0.08212278 - time (sec): 81.39 - samples/sec: 2316.72 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-14 19:12:33,816 epoch 3 - iter 2166/3617 - loss 0.08334289 - time (sec): 97.71 - samples/sec: 2326.30 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-14 19:12:50,145 epoch 3 - iter 2527/3617 - loss 0.08219281 - time (sec): 114.04 - samples/sec: 2331.35 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-14 19:13:06,352 epoch 3 - iter 2888/3617 - loss 0.08216017 - time (sec): 130.24 - samples/sec: 2329.63 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-14 19:13:23,473 epoch 3 - iter 3249/3617 - loss 0.08248407 - time (sec): 147.37 - samples/sec: 2313.36 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-14 19:13:39,840 epoch 3 - iter 3610/3617 - loss 0.08153553 - time (sec): 163.73 - samples/sec: 2316.89 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-14 19:13:40,153 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-14 19:13:40,153 EPOCH 3 done: loss 0.0815 - lr: 0.000039
118
+ 2023-10-14 19:13:46,359 DEV : loss 0.18807156383991241 - f1-score (micro avg) 0.6297
119
+ 2023-10-14 19:13:46,388 saving best model
120
+ 2023-10-14 19:13:46,968 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-14 19:14:03,475 epoch 4 - iter 361/3617 - loss 0.06057895 - time (sec): 16.50 - samples/sec: 2377.22 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-14 19:14:19,869 epoch 4 - iter 722/3617 - loss 0.06057279 - time (sec): 32.90 - samples/sec: 2329.53 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-14 19:14:36,163 epoch 4 - iter 1083/3617 - loss 0.06014925 - time (sec): 49.19 - samples/sec: 2321.32 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-14 19:14:52,280 epoch 4 - iter 1444/3617 - loss 0.06060661 - time (sec): 65.31 - samples/sec: 2305.72 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-14 19:15:08,428 epoch 4 - iter 1805/3617 - loss 0.06034321 - time (sec): 81.46 - samples/sec: 2323.14 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-14 19:15:24,537 epoch 4 - iter 2166/3617 - loss 0.06055420 - time (sec): 97.57 - samples/sec: 2322.80 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-14 19:15:40,905 epoch 4 - iter 2527/3617 - loss 0.06148213 - time (sec): 113.93 - samples/sec: 2325.01 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-14 19:15:57,092 epoch 4 - iter 2888/3617 - loss 0.06126538 - time (sec): 130.12 - samples/sec: 2331.57 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-14 19:16:13,259 epoch 4 - iter 3249/3617 - loss 0.06194798 - time (sec): 146.29 - samples/sec: 2334.61 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-14 19:16:29,462 epoch 4 - iter 3610/3617 - loss 0.06151356 - time (sec): 162.49 - samples/sec: 2333.50 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-14 19:16:29,772 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-14 19:16:29,773 EPOCH 4 done: loss 0.0614 - lr: 0.000033
133
+ 2023-10-14 19:16:35,943 DEV : loss 0.2195165902376175 - f1-score (micro avg) 0.6197
134
+ 2023-10-14 19:16:35,973 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-14 19:16:52,484 epoch 5 - iter 361/3617 - loss 0.04617918 - time (sec): 16.51 - samples/sec: 2385.58 - lr: 0.000033 - momentum: 0.000000
136
+ 2023-10-14 19:17:08,608 epoch 5 - iter 722/3617 - loss 0.04463891 - time (sec): 32.63 - samples/sec: 2362.80 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-14 19:17:24,908 epoch 5 - iter 1083/3617 - loss 0.04774820 - time (sec): 48.93 - samples/sec: 2352.31 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-14 19:17:41,128 epoch 5 - iter 1444/3617 - loss 0.04829543 - time (sec): 65.15 - samples/sec: 2331.91 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-14 19:17:57,525 epoch 5 - iter 1805/3617 - loss 0.04629774 - time (sec): 81.55 - samples/sec: 2341.74 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-14 19:18:13,880 epoch 5 - iter 2166/3617 - loss 0.04539649 - time (sec): 97.91 - samples/sec: 2342.96 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-14 19:18:30,165 epoch 5 - iter 2527/3617 - loss 0.04517893 - time (sec): 114.19 - samples/sec: 2345.27 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-14 19:18:46,313 epoch 5 - iter 2888/3617 - loss 0.04431891 - time (sec): 130.34 - samples/sec: 2337.69 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-14 19:19:02,438 epoch 5 - iter 3249/3617 - loss 0.04447990 - time (sec): 146.46 - samples/sec: 2341.40 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-14 19:19:18,521 epoch 5 - iter 3610/3617 - loss 0.04436946 - time (sec): 162.55 - samples/sec: 2333.42 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-14 19:19:18,823 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-14 19:19:18,823 EPOCH 5 done: loss 0.0443 - lr: 0.000028
147
+ 2023-10-14 19:19:25,023 DEV : loss 0.3201915919780731 - f1-score (micro avg) 0.6218
148
+ 2023-10-14 19:19:25,052 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-14 19:19:41,359 epoch 6 - iter 361/3617 - loss 0.02847515 - time (sec): 16.31 - samples/sec: 2328.31 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-14 19:19:57,743 epoch 6 - iter 722/3617 - loss 0.03162381 - time (sec): 32.69 - samples/sec: 2301.42 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-14 19:20:13,935 epoch 6 - iter 1083/3617 - loss 0.03126177 - time (sec): 48.88 - samples/sec: 2288.28 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-14 19:20:30,140 epoch 6 - iter 1444/3617 - loss 0.03237564 - time (sec): 65.09 - samples/sec: 2296.72 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-14 19:20:46,426 epoch 6 - iter 1805/3617 - loss 0.03357153 - time (sec): 81.37 - samples/sec: 2314.60 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-14 19:21:02,702 epoch 6 - iter 2166/3617 - loss 0.03474249 - time (sec): 97.65 - samples/sec: 2321.83 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-14 19:21:18,924 epoch 6 - iter 2527/3617 - loss 0.03416368 - time (sec): 113.87 - samples/sec: 2318.63 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-14 19:21:35,300 epoch 6 - iter 2888/3617 - loss 0.03478335 - time (sec): 130.25 - samples/sec: 2333.53 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-14 19:21:51,568 epoch 6 - iter 3249/3617 - loss 0.03429456 - time (sec): 146.51 - samples/sec: 2326.16 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-14 19:22:07,803 epoch 6 - iter 3610/3617 - loss 0.03403117 - time (sec): 162.75 - samples/sec: 2330.17 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-14 19:22:08,110 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-14 19:22:08,110 EPOCH 6 done: loss 0.0340 - lr: 0.000022
161
+ 2023-10-14 19:22:13,840 DEV : loss 0.295797199010849 - f1-score (micro avg) 0.6353
162
+ 2023-10-14 19:22:13,873 saving best model
163
+ 2023-10-14 19:22:15,198 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-14 19:22:31,709 epoch 7 - iter 361/3617 - loss 0.01782055 - time (sec): 16.51 - samples/sec: 2349.80 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-14 19:22:48,225 epoch 7 - iter 722/3617 - loss 0.02038942 - time (sec): 33.02 - samples/sec: 2334.00 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-14 19:23:04,594 epoch 7 - iter 1083/3617 - loss 0.02125683 - time (sec): 49.39 - samples/sec: 2328.23 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-14 19:23:20,803 epoch 7 - iter 1444/3617 - loss 0.02186389 - time (sec): 65.60 - samples/sec: 2329.56 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-14 19:23:37,105 epoch 7 - iter 1805/3617 - loss 0.02286446 - time (sec): 81.90 - samples/sec: 2327.67 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-14 19:23:53,394 epoch 7 - iter 2166/3617 - loss 0.02265517 - time (sec): 98.19 - samples/sec: 2327.00 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-14 19:24:09,594 epoch 7 - iter 2527/3617 - loss 0.02328181 - time (sec): 114.39 - samples/sec: 2325.06 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-14 19:24:25,973 epoch 7 - iter 2888/3617 - loss 0.02329662 - time (sec): 130.77 - samples/sec: 2325.37 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-14 19:24:42,223 epoch 7 - iter 3249/3617 - loss 0.02335070 - time (sec): 147.02 - samples/sec: 2321.86 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-14 19:24:58,552 epoch 7 - iter 3610/3617 - loss 0.02367072 - time (sec): 163.35 - samples/sec: 2321.55 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-14 19:24:58,858 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-14 19:24:58,858 EPOCH 7 done: loss 0.0237 - lr: 0.000017
176
+ 2023-10-14 19:25:04,434 DEV : loss 0.2667960822582245 - f1-score (micro avg) 0.6398
177
+ 2023-10-14 19:25:04,468 saving best model
178
+ 2023-10-14 19:25:05,056 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-14 19:25:21,333 epoch 8 - iter 361/3617 - loss 0.01420959 - time (sec): 16.27 - samples/sec: 2271.05 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-14 19:25:37,646 epoch 8 - iter 722/3617 - loss 0.01438499 - time (sec): 32.59 - samples/sec: 2300.97 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-14 19:25:54,010 epoch 8 - iter 1083/3617 - loss 0.01612726 - time (sec): 48.95 - samples/sec: 2324.11 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-14 19:26:10,324 epoch 8 - iter 1444/3617 - loss 0.01522163 - time (sec): 65.26 - samples/sec: 2323.82 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-14 19:26:26,522 epoch 8 - iter 1805/3617 - loss 0.01523890 - time (sec): 81.46 - samples/sec: 2319.15 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-14 19:26:42,609 epoch 8 - iter 2166/3617 - loss 0.01636181 - time (sec): 97.55 - samples/sec: 2301.16 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-14 19:26:59,146 epoch 8 - iter 2527/3617 - loss 0.01647260 - time (sec): 114.09 - samples/sec: 2313.61 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-14 19:27:15,466 epoch 8 - iter 2888/3617 - loss 0.01588100 - time (sec): 130.41 - samples/sec: 2311.13 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-14 19:27:31,824 epoch 8 - iter 3249/3617 - loss 0.01566046 - time (sec): 146.76 - samples/sec: 2319.16 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-14 19:27:48,117 epoch 8 - iter 3610/3617 - loss 0.01532074 - time (sec): 163.06 - samples/sec: 2325.05 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-14 19:27:48,435 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-14 19:27:48,435 EPOCH 8 done: loss 0.0153 - lr: 0.000011
191
+ 2023-10-14 19:27:54,685 DEV : loss 0.3515782952308655 - f1-score (micro avg) 0.6337
192
+ 2023-10-14 19:27:54,715 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-14 19:28:11,336 epoch 9 - iter 361/3617 - loss 0.01078017 - time (sec): 16.62 - samples/sec: 2283.55 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-14 19:28:27,693 epoch 9 - iter 722/3617 - loss 0.01382949 - time (sec): 32.98 - samples/sec: 2335.85 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-14 19:28:43,933 epoch 9 - iter 1083/3617 - loss 0.01233271 - time (sec): 49.22 - samples/sec: 2346.52 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-14 19:29:00,350 epoch 9 - iter 1444/3617 - loss 0.01223895 - time (sec): 65.63 - samples/sec: 2317.17 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-14 19:29:16,569 epoch 9 - iter 1805/3617 - loss 0.01153695 - time (sec): 81.85 - samples/sec: 2317.35 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-14 19:29:32,978 epoch 9 - iter 2166/3617 - loss 0.01075403 - time (sec): 98.26 - samples/sec: 2311.68 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-14 19:29:49,302 epoch 9 - iter 2527/3617 - loss 0.01022522 - time (sec): 114.59 - samples/sec: 2302.94 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-14 19:30:05,794 epoch 9 - iter 2888/3617 - loss 0.01001724 - time (sec): 131.08 - samples/sec: 2302.46 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-14 19:30:22,232 epoch 9 - iter 3249/3617 - loss 0.01004538 - time (sec): 147.52 - samples/sec: 2308.06 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-14 19:30:38,601 epoch 9 - iter 3610/3617 - loss 0.00979458 - time (sec): 163.88 - samples/sec: 2314.28 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-14 19:30:38,911 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-14 19:30:38,911 EPOCH 9 done: loss 0.0098 - lr: 0.000006
205
+ 2023-10-14 19:30:45,203 DEV : loss 0.365791916847229 - f1-score (micro avg) 0.6403
206
+ 2023-10-14 19:30:45,260 saving best model
207
+ 2023-10-14 19:30:45,882 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-14 19:31:02,260 epoch 10 - iter 361/3617 - loss 0.00465788 - time (sec): 16.38 - samples/sec: 2343.20 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-14 19:31:18,604 epoch 10 - iter 722/3617 - loss 0.00449815 - time (sec): 32.72 - samples/sec: 2361.91 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-14 19:31:34,930 epoch 10 - iter 1083/3617 - loss 0.00507346 - time (sec): 49.05 - samples/sec: 2330.64 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-14 19:31:51,267 epoch 10 - iter 1444/3617 - loss 0.00557339 - time (sec): 65.38 - samples/sec: 2328.26 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-14 19:32:07,730 epoch 10 - iter 1805/3617 - loss 0.00531563 - time (sec): 81.85 - samples/sec: 2328.59 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-14 19:32:24,093 epoch 10 - iter 2166/3617 - loss 0.00641317 - time (sec): 98.21 - samples/sec: 2330.04 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-14 19:32:40,290 epoch 10 - iter 2527/3617 - loss 0.00595602 - time (sec): 114.41 - samples/sec: 2318.77 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-14 19:32:56,448 epoch 10 - iter 2888/3617 - loss 0.00598682 - time (sec): 130.56 - samples/sec: 2304.67 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-14 19:33:12,731 epoch 10 - iter 3249/3617 - loss 0.00596379 - time (sec): 146.85 - samples/sec: 2312.77 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-14 19:33:29,112 epoch 10 - iter 3610/3617 - loss 0.00609464 - time (sec): 163.23 - samples/sec: 2323.98 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-14 19:33:29,412 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-14 19:33:29,412 EPOCH 10 done: loss 0.0061 - lr: 0.000000
220
+ 2023-10-14 19:33:35,636 DEV : loss 0.3828698396682739 - f1-score (micro avg) 0.6321
221
+ 2023-10-14 19:33:36,042 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-14 19:33:36,043 Loading model from best epoch ...
223
+ 2023-10-14 19:33:37,423 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
224
+ 2023-10-14 19:33:44,142
225
+ Results:
226
+ - F-score (micro) 0.6452
227
+ - F-score (macro) 0.4857
228
+ - Accuracy 0.4899
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ loc 0.6283 0.8037 0.7053 591
234
+ pers 0.5526 0.7507 0.6366 357
235
+ org 0.1333 0.1013 0.1151 79
236
+
237
+ micro avg 0.5772 0.7313 0.6452 1027
238
+ macro avg 0.4381 0.5519 0.4857 1027
239
+ weighted avg 0.5639 0.7313 0.6360 1027
240
+
241
+ 2023-10-14 19:33:44,142 ----------------------------------------------------------------------------------------------------