Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
33e0e27
·
1 Parent(s): e4f6af4

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 +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd94eb9f7ca6995b28d3e1d6cadf7d6f13ab34d3c7cd63b0e2a636bcf4a7255e
3
+ size 443335879
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 15:29:07 0.0000 0.5556 0.1404 0.6832 0.7497 0.7149 0.5844
3
+ 2 15:30:30 0.0000 0.1285 0.1445 0.7533 0.7749 0.7640 0.6558
4
+ 3 15:31:54 0.0000 0.0834 0.1618 0.7866 0.8213 0.8036 0.6978
5
+ 4 15:33:15 0.0000 0.0577 0.1881 0.7696 0.8379 0.8023 0.6921
6
+ 5 15:34:38 0.0000 0.0409 0.1835 0.7994 0.8288 0.8138 0.7188
7
+ 6 15:36:00 0.0000 0.0314 0.1998 0.7966 0.8253 0.8107 0.7141
8
+ 7 15:37:22 0.0000 0.0215 0.2015 0.8209 0.8402 0.8305 0.7368
9
+ 8 15:38:44 0.0000 0.0136 0.2002 0.8285 0.8328 0.8306 0.7358
10
+ 9 15:40:07 0.0000 0.0095 0.2112 0.8216 0.8414 0.8314 0.7427
11
+ 10 15:41:33 0.0000 0.0059 0.2184 0.8234 0.8333 0.8284 0.7360
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 15:27:51,374 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 15:27:51,375 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=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 15:27:51,375 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 15:27:51,375 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
+ 2023-10-13 15:27:51,375 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 15:27:51,375 Train: 5901 sentences
55
+ 2023-10-13 15:27:51,375 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 15:27:51,375 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 15:27:51,375 Training Params:
58
+ 2023-10-13 15:27:51,375 - learning_rate: "3e-05"
59
+ 2023-10-13 15:27:51,375 - mini_batch_size: "4"
60
+ 2023-10-13 15:27:51,375 - max_epochs: "10"
61
+ 2023-10-13 15:27:51,375 - shuffle: "True"
62
+ 2023-10-13 15:27:51,375 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 15:27:51,375 Plugins:
64
+ 2023-10-13 15:27:51,375 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 15:27:51,375 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 15:27:51,376 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 15:27:51,376 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 15:27:51,376 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 15:27:51,376 Computation:
70
+ 2023-10-13 15:27:51,376 - compute on device: cuda:0
71
+ 2023-10-13 15:27:51,376 - embedding storage: none
72
+ 2023-10-13 15:27:51,376 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 15:27:51,376 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 15:27:51,376 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 15:27:51,376 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 15:27:58,575 epoch 1 - iter 147/1476 - loss 2.67128935 - time (sec): 7.20 - samples/sec: 2344.96 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 15:28:05,440 epoch 1 - iter 294/1476 - loss 1.66437545 - time (sec): 14.06 - samples/sec: 2356.83 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 15:28:12,862 epoch 1 - iter 441/1476 - loss 1.24057897 - time (sec): 21.49 - samples/sec: 2436.27 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 15:28:19,562 epoch 1 - iter 588/1476 - loss 1.03733344 - time (sec): 28.19 - samples/sec: 2390.97 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 15:28:26,431 epoch 1 - iter 735/1476 - loss 0.89839028 - time (sec): 35.05 - samples/sec: 2384.70 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 15:28:33,323 epoch 1 - iter 882/1476 - loss 0.79874819 - time (sec): 41.95 - samples/sec: 2361.49 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 15:28:40,075 epoch 1 - iter 1029/1476 - loss 0.72454902 - time (sec): 48.70 - samples/sec: 2347.97 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 15:28:46,841 epoch 1 - iter 1176/1476 - loss 0.66241525 - time (sec): 55.46 - samples/sec: 2338.34 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 15:28:54,229 epoch 1 - iter 1323/1476 - loss 0.59924863 - time (sec): 62.85 - samples/sec: 2372.82 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 15:29:01,448 epoch 1 - iter 1470/1476 - loss 0.55709201 - time (sec): 70.07 - samples/sec: 2366.27 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 15:29:01,707 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 15:29:01,708 EPOCH 1 done: loss 0.5556 - lr: 0.000030
88
+ 2023-10-13 15:29:07,863 DEV : loss 0.14035969972610474 - f1-score (micro avg) 0.7149
89
+ 2023-10-13 15:29:07,892 saving best model
90
+ 2023-10-13 15:29:08,465 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 15:29:15,669 epoch 2 - iter 147/1476 - loss 0.15079759 - time (sec): 7.20 - samples/sec: 2360.12 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 15:29:22,670 epoch 2 - iter 294/1476 - loss 0.14126703 - time (sec): 14.20 - samples/sec: 2200.45 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 15:29:29,499 epoch 2 - iter 441/1476 - loss 0.14626876 - time (sec): 21.03 - samples/sec: 2222.41 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 15:29:36,399 epoch 2 - iter 588/1476 - loss 0.14067959 - time (sec): 27.93 - samples/sec: 2257.92 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 15:29:43,088 epoch 2 - iter 735/1476 - loss 0.13794568 - time (sec): 34.62 - samples/sec: 2263.69 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 15:29:51,009 epoch 2 - iter 882/1476 - loss 0.13937727 - time (sec): 42.54 - samples/sec: 2355.76 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 15:29:58,281 epoch 2 - iter 1029/1476 - loss 0.13468420 - time (sec): 49.81 - samples/sec: 2350.07 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 15:30:05,519 epoch 2 - iter 1176/1476 - loss 0.13405240 - time (sec): 57.05 - samples/sec: 2334.43 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 15:30:12,368 epoch 2 - iter 1323/1476 - loss 0.13202783 - time (sec): 63.90 - samples/sec: 2345.98 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 15:30:19,112 epoch 2 - iter 1470/1476 - loss 0.12858037 - time (sec): 70.65 - samples/sec: 2348.15 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 15:30:19,372 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 15:30:19,372 EPOCH 2 done: loss 0.1285 - lr: 0.000027
103
+ 2023-10-13 15:30:30,473 DEV : loss 0.1444912701845169 - f1-score (micro avg) 0.764
104
+ 2023-10-13 15:30:30,501 saving best model
105
+ 2023-10-13 15:30:31,009 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 15:30:38,496 epoch 3 - iter 147/1476 - loss 0.08029554 - time (sec): 7.48 - samples/sec: 2048.88 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 15:30:46,516 epoch 3 - iter 294/1476 - loss 0.07686342 - time (sec): 15.50 - samples/sec: 2024.98 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 15:30:53,679 epoch 3 - iter 441/1476 - loss 0.07956883 - time (sec): 22.66 - samples/sec: 2142.91 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 15:31:00,854 epoch 3 - iter 588/1476 - loss 0.08463364 - time (sec): 29.84 - samples/sec: 2205.98 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 15:31:07,976 epoch 3 - iter 735/1476 - loss 0.08625536 - time (sec): 36.96 - samples/sec: 2256.21 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 15:31:14,723 epoch 3 - iter 882/1476 - loss 0.08680712 - time (sec): 43.71 - samples/sec: 2253.30 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 15:31:21,639 epoch 3 - iter 1029/1476 - loss 0.08602669 - time (sec): 50.62 - samples/sec: 2279.35 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 15:31:28,731 epoch 3 - iter 1176/1476 - loss 0.08666656 - time (sec): 57.72 - samples/sec: 2289.82 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 15:31:35,604 epoch 3 - iter 1323/1476 - loss 0.08609219 - time (sec): 64.59 - samples/sec: 2302.44 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 15:31:42,847 epoch 3 - iter 1470/1476 - loss 0.08337165 - time (sec): 71.83 - samples/sec: 2310.10 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 15:31:43,113 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 15:31:43,114 EPOCH 3 done: loss 0.0834 - lr: 0.000023
118
+ 2023-10-13 15:31:54,210 DEV : loss 0.161760613322258 - f1-score (micro avg) 0.8036
119
+ 2023-10-13 15:31:54,239 saving best model
120
+ 2023-10-13 15:31:55,198 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 15:32:02,152 epoch 4 - iter 147/1476 - loss 0.05876058 - time (sec): 6.95 - samples/sec: 2278.92 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 15:32:09,259 epoch 4 - iter 294/1476 - loss 0.05569616 - time (sec): 14.06 - samples/sec: 2387.95 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 15:32:16,572 epoch 4 - iter 441/1476 - loss 0.05615460 - time (sec): 21.37 - samples/sec: 2462.00 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 15:32:23,371 epoch 4 - iter 588/1476 - loss 0.05297739 - time (sec): 28.17 - samples/sec: 2406.73 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 15:32:29,991 epoch 4 - iter 735/1476 - loss 0.05364302 - time (sec): 34.79 - samples/sec: 2397.48 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 15:32:36,439 epoch 4 - iter 882/1476 - loss 0.05261850 - time (sec): 41.24 - samples/sec: 2377.08 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 15:32:43,387 epoch 4 - iter 1029/1476 - loss 0.05432762 - time (sec): 48.19 - samples/sec: 2408.94 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 15:32:49,923 epoch 4 - iter 1176/1476 - loss 0.05493788 - time (sec): 54.72 - samples/sec: 2397.34 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 15:32:57,077 epoch 4 - iter 1323/1476 - loss 0.05561241 - time (sec): 61.88 - samples/sec: 2410.01 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 15:33:04,188 epoch 4 - iter 1470/1476 - loss 0.05782730 - time (sec): 68.99 - samples/sec: 2403.75 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 15:33:04,442 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 15:33:04,442 EPOCH 4 done: loss 0.0577 - lr: 0.000020
133
+ 2023-10-13 15:33:15,617 DEV : loss 0.18805062770843506 - f1-score (micro avg) 0.8023
134
+ 2023-10-13 15:33:15,646 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-13 15:33:22,434 epoch 5 - iter 147/1476 - loss 0.04212635 - time (sec): 6.79 - samples/sec: 2269.00 - lr: 0.000020 - momentum: 0.000000
136
+ 2023-10-13 15:33:29,485 epoch 5 - iter 294/1476 - loss 0.03671755 - time (sec): 13.84 - samples/sec: 2274.14 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-13 15:33:37,084 epoch 5 - iter 441/1476 - loss 0.04111502 - time (sec): 21.44 - samples/sec: 2277.13 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 15:33:44,549 epoch 5 - iter 588/1476 - loss 0.03769225 - time (sec): 28.90 - samples/sec: 2236.07 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 15:33:51,684 epoch 5 - iter 735/1476 - loss 0.03738604 - time (sec): 36.04 - samples/sec: 2280.93 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-13 15:33:58,651 epoch 5 - iter 882/1476 - loss 0.03956318 - time (sec): 43.00 - samples/sec: 2301.19 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 15:34:05,493 epoch 5 - iter 1029/1476 - loss 0.04047921 - time (sec): 49.85 - samples/sec: 2297.13 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 15:34:12,761 epoch 5 - iter 1176/1476 - loss 0.04008186 - time (sec): 57.11 - samples/sec: 2326.24 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-13 15:34:19,761 epoch 5 - iter 1323/1476 - loss 0.03983351 - time (sec): 64.11 - samples/sec: 2328.16 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 15:34:26,671 epoch 5 - iter 1470/1476 - loss 0.04072459 - time (sec): 71.02 - samples/sec: 2335.98 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 15:34:26,963 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-13 15:34:26,963 EPOCH 5 done: loss 0.0409 - lr: 0.000017
147
+ 2023-10-13 15:34:38,138 DEV : loss 0.18352609872817993 - f1-score (micro avg) 0.8138
148
+ 2023-10-13 15:34:38,175 saving best model
149
+ 2023-10-13 15:34:38,693 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 15:34:45,597 epoch 6 - iter 147/1476 - loss 0.03301350 - time (sec): 6.90 - samples/sec: 2180.03 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-13 15:34:52,473 epoch 6 - iter 294/1476 - loss 0.03217606 - time (sec): 13.77 - samples/sec: 2226.65 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 15:34:59,887 epoch 6 - iter 441/1476 - loss 0.03175343 - time (sec): 21.19 - samples/sec: 2327.75 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 15:35:07,067 epoch 6 - iter 588/1476 - loss 0.03347640 - time (sec): 28.37 - samples/sec: 2316.77 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-13 15:35:14,095 epoch 6 - iter 735/1476 - loss 0.03623768 - time (sec): 35.40 - samples/sec: 2321.80 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 15:35:21,146 epoch 6 - iter 882/1476 - loss 0.03364347 - time (sec): 42.45 - samples/sec: 2347.80 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 15:35:27,964 epoch 6 - iter 1029/1476 - loss 0.03302726 - time (sec): 49.26 - samples/sec: 2330.39 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-13 15:35:34,863 epoch 6 - iter 1176/1476 - loss 0.03257321 - time (sec): 56.16 - samples/sec: 2333.46 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 15:35:42,265 epoch 6 - iter 1323/1476 - loss 0.03242265 - time (sec): 63.57 - samples/sec: 2361.98 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 15:35:49,114 epoch 6 - iter 1470/1476 - loss 0.03154020 - time (sec): 70.41 - samples/sec: 2355.93 - lr: 0.000013 - momentum: 0.000000
160
+ 2023-10-13 15:35:49,382 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 15:35:49,383 EPOCH 6 done: loss 0.0314 - lr: 0.000013
162
+ 2023-10-13 15:36:00,508 DEV : loss 0.19981108605861664 - f1-score (micro avg) 0.8107
163
+ 2023-10-13 15:36:00,539 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-13 15:36:07,373 epoch 7 - iter 147/1476 - loss 0.02210395 - time (sec): 6.83 - samples/sec: 2244.86 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-13 15:36:14,809 epoch 7 - iter 294/1476 - loss 0.02469555 - time (sec): 14.27 - samples/sec: 2376.50 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 15:36:21,619 epoch 7 - iter 441/1476 - loss 0.02162633 - time (sec): 21.08 - samples/sec: 2330.74 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-13 15:36:28,788 epoch 7 - iter 588/1476 - loss 0.02184522 - time (sec): 28.25 - samples/sec: 2320.49 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 15:36:36,140 epoch 7 - iter 735/1476 - loss 0.02211174 - time (sec): 35.60 - samples/sec: 2309.65 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 15:36:43,577 epoch 7 - iter 882/1476 - loss 0.02359508 - time (sec): 43.04 - samples/sec: 2338.18 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-13 15:36:50,676 epoch 7 - iter 1029/1476 - loss 0.02284324 - time (sec): 50.14 - samples/sec: 2361.36 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 15:36:57,732 epoch 7 - iter 1176/1476 - loss 0.02153323 - time (sec): 57.19 - samples/sec: 2358.44 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 15:37:04,473 epoch 7 - iter 1323/1476 - loss 0.02137460 - time (sec): 63.93 - samples/sec: 2343.49 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-13 15:37:11,276 epoch 7 - iter 1470/1476 - loss 0.02141477 - time (sec): 70.74 - samples/sec: 2345.11 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 15:37:11,571 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-13 15:37:11,571 EPOCH 7 done: loss 0.0215 - lr: 0.000010
176
+ 2023-10-13 15:37:22,751 DEV : loss 0.20148473978042603 - f1-score (micro avg) 0.8305
177
+ 2023-10-13 15:37:22,780 saving best model
178
+ 2023-10-13 15:37:23,262 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-13 15:37:30,423 epoch 8 - iter 147/1476 - loss 0.01204328 - time (sec): 7.16 - samples/sec: 2281.23 - lr: 0.000010 - momentum: 0.000000
180
+ 2023-10-13 15:37:37,180 epoch 8 - iter 294/1476 - loss 0.01038902 - time (sec): 13.91 - samples/sec: 2309.22 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-13 15:37:44,247 epoch 8 - iter 441/1476 - loss 0.01128180 - time (sec): 20.98 - samples/sec: 2379.03 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 15:37:51,183 epoch 8 - iter 588/1476 - loss 0.01249804 - time (sec): 27.92 - samples/sec: 2360.92 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 15:37:58,038 epoch 8 - iter 735/1476 - loss 0.01344434 - time (sec): 34.77 - samples/sec: 2353.59 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-13 15:38:04,979 epoch 8 - iter 882/1476 - loss 0.01407197 - time (sec): 41.71 - samples/sec: 2342.83 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 15:38:11,924 epoch 8 - iter 1029/1476 - loss 0.01397679 - time (sec): 48.66 - samples/sec: 2334.81 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 15:38:19,217 epoch 8 - iter 1176/1476 - loss 0.01440414 - time (sec): 55.95 - samples/sec: 2355.21 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-13 15:38:26,144 epoch 8 - iter 1323/1476 - loss 0.01412839 - time (sec): 62.88 - samples/sec: 2359.61 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 15:38:33,233 epoch 8 - iter 1470/1476 - loss 0.01337390 - time (sec): 69.97 - samples/sec: 2371.84 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 15:38:33,482 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-13 15:38:33,482 EPOCH 8 done: loss 0.0136 - lr: 0.000007
191
+ 2023-10-13 15:38:44,536 DEV : loss 0.20017683506011963 - f1-score (micro avg) 0.8306
192
+ 2023-10-13 15:38:44,565 saving best model
193
+ 2023-10-13 15:38:45,121 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-13 15:38:52,432 epoch 9 - iter 147/1476 - loss 0.00826798 - time (sec): 7.31 - samples/sec: 2380.38 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 15:38:59,260 epoch 9 - iter 294/1476 - loss 0.00873267 - time (sec): 14.14 - samples/sec: 2393.03 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 15:39:06,139 epoch 9 - iter 441/1476 - loss 0.01108423 - time (sec): 21.02 - samples/sec: 2357.23 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 15:39:13,148 epoch 9 - iter 588/1476 - loss 0.00932900 - time (sec): 28.03 - samples/sec: 2351.45 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 15:39:20,508 epoch 9 - iter 735/1476 - loss 0.00942840 - time (sec): 35.39 - samples/sec: 2319.05 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 15:39:27,548 epoch 9 - iter 882/1476 - loss 0.00936287 - time (sec): 42.43 - samples/sec: 2299.14 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 15:39:34,580 epoch 9 - iter 1029/1476 - loss 0.00958077 - time (sec): 49.46 - samples/sec: 2324.33 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 15:39:41,934 epoch 9 - iter 1176/1476 - loss 0.00917407 - time (sec): 56.81 - samples/sec: 2329.00 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 15:39:48,949 epoch 9 - iter 1323/1476 - loss 0.00951637 - time (sec): 63.83 - samples/sec: 2333.50 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 15:39:55,997 epoch 9 - iter 1470/1476 - loss 0.00949339 - time (sec): 70.87 - samples/sec: 2341.48 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-13 15:39:56,255 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-13 15:39:56,255 EPOCH 9 done: loss 0.0095 - lr: 0.000003
206
+ 2023-10-13 15:40:07,445 DEV : loss 0.21117821335792542 - f1-score (micro avg) 0.8314
207
+ 2023-10-13 15:40:07,474 saving best model
208
+ 2023-10-13 15:40:08,082 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 15:40:14,953 epoch 10 - iter 147/1476 - loss 0.00930289 - time (sec): 6.86 - samples/sec: 2352.47 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 15:40:24,876 epoch 10 - iter 294/1476 - loss 0.00642253 - time (sec): 16.79 - samples/sec: 2124.43 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 15:40:31,972 epoch 10 - iter 441/1476 - loss 0.00573633 - time (sec): 23.88 - samples/sec: 2164.66 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 15:40:38,711 epoch 10 - iter 588/1476 - loss 0.00534887 - time (sec): 30.62 - samples/sec: 2199.43 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 15:40:45,486 epoch 10 - iter 735/1476 - loss 0.00493565 - time (sec): 37.40 - samples/sec: 2211.92 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 15:40:52,210 epoch 10 - iter 882/1476 - loss 0.00519681 - time (sec): 44.12 - samples/sec: 2220.79 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 15:40:59,407 epoch 10 - iter 1029/1476 - loss 0.00566250 - time (sec): 51.32 - samples/sec: 2248.33 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 15:41:06,385 epoch 10 - iter 1176/1476 - loss 0.00599606 - time (sec): 58.30 - samples/sec: 2261.89 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 15:41:13,308 epoch 10 - iter 1323/1476 - loss 0.00567523 - time (sec): 65.22 - samples/sec: 2267.40 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 15:41:21,239 epoch 10 - iter 1470/1476 - loss 0.00589442 - time (sec): 73.15 - samples/sec: 2269.93 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 15:41:21,549 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 15:41:21,549 EPOCH 10 done: loss 0.0059 - lr: 0.000000
221
+ 2023-10-13 15:41:33,106 DEV : loss 0.2184198498725891 - f1-score (micro avg) 0.8284
222
+ 2023-10-13 15:41:33,638 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 15:41:33,640 Loading model from best epoch ...
224
+ 2023-10-13 15:41:35,214 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
225
+ 2023-10-13 15:41:41,298
226
+ Results:
227
+ - F-score (micro) 0.7927
228
+ - F-score (macro) 0.6875
229
+ - Accuracy 0.6802
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8710 0.8660 0.8685 858
235
+ pers 0.7522 0.7970 0.7740 537
236
+ org 0.5127 0.6136 0.5586 132
237
+ prod 0.6724 0.6393 0.6555 61
238
+ time 0.5397 0.6296 0.5812 54
239
+
240
+ micro avg 0.7790 0.8069 0.7927 1642
241
+ macro avg 0.6696 0.7091 0.6875 1642
242
+ weighted avg 0.7851 0.8069 0.7953 1642
243
+
244
+ 2023-10-13 15:41:41,299 ----------------------------------------------------------------------------------------------------