Hugging Face's logo

stefan-it
/
flair-clean-conll-3

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Model card Files Metrics Community
stefan-it commited on
Commit
c15ad03
•
1 Parent(s): 4702094

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +244 -0
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-27 17:20:54,808 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-27 17:20:54,809 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): XLMRobertaModel(
5
+ (embeddings): XLMRobertaEmbeddings(
6
+ (word_embeddings): Embedding(250003, 1024)
7
+ (position_embeddings): Embedding(514, 1024, padding_idx=1)
8
+ (token_type_embeddings): Embedding(1, 1024)
9
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): XLMRobertaEncoder(
13
+ (layer): ModuleList(
14
+ (0-23): 24 x XLMRobertaLayer(
15
+ (attention): XLMRobertaAttention(
16
+ (self): XLMRobertaSelfAttention(
17
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
18
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
19
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): XLMRobertaSelfOutput(
23
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
24
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): XLMRobertaIntermediate(
29
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): XLMRobertaOutput(
33
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
34
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): XLMRobertaPooler(
41
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=1024, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-27 17:20:54,809 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-27 17:20:54,809 Corpus: 14903 train + 3449 dev + 3658 test sentences
52
+ 2023-10-27 17:20:54,809 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-27 17:20:54,809 Train: 14903 sentences
54
+ 2023-10-27 17:20:54,809 (train_with_dev=False, train_with_test=False)
55
+ 2023-10-27 17:20:54,809 ----------------------------------------------------------------------------------------------------
56
+ 2023-10-27 17:20:54,809 Training Params:
57
+ 2023-10-27 17:20:54,809 - learning_rate: "5e-06"
58
+ 2023-10-27 17:20:54,809 - mini_batch_size: "4"
59
+ 2023-10-27 17:20:54,809 - max_epochs: "10"
60
+ 2023-10-27 17:20:54,809 - shuffle: "True"
61
+ 2023-10-27 17:20:54,810 ----------------------------------------------------------------------------------------------------
62
+ 2023-10-27 17:20:54,810 Plugins:
63
+ 2023-10-27 17:20:54,810 - TensorboardLogger
64
+ 2023-10-27 17:20:54,810 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-27 17:20:54,810 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-27 17:20:54,810 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-27 17:20:54,810 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-27 17:20:54,810 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-27 17:20:54,810 Computation:
70
+ 2023-10-27 17:20:54,810 - compute on device: cuda:0
71
+ 2023-10-27 17:20:54,810 - embedding storage: none
72
+ 2023-10-27 17:20:54,810 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-27 17:20:54,810 Model training base path: "flair-clean-conll-lr5e-06-bs4-3"
74
+ 2023-10-27 17:20:54,810 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-27 17:20:54,810 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-27 17:20:54,810 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2023-10-27 17:21:40,162 epoch 1 - iter 372/3726 - loss 2.98651987 - time (sec): 45.35 - samples/sec: 437.70 - lr: 0.000000 - momentum: 0.000000
78
+ 2023-10-27 17:22:25,895 epoch 1 - iter 744/3726 - loss 1.95456152 - time (sec): 91.08 - samples/sec: 446.47 - lr: 0.000001 - momentum: 0.000000
79
+ 2023-10-27 17:23:14,767 epoch 1 - iter 1116/3726 - loss 1.47436963 - time (sec): 139.96 - samples/sec: 438.22 - lr: 0.000001 - momentum: 0.000000
80
+ 2023-10-27 17:24:00,286 epoch 1 - iter 1488/3726 - loss 1.21396490 - time (sec): 185.47 - samples/sec: 440.46 - lr: 0.000002 - momentum: 0.000000
81
+ 2023-10-27 17:24:46,086 epoch 1 - iter 1860/3726 - loss 1.02707175 - time (sec): 231.27 - samples/sec: 442.97 - lr: 0.000002 - momentum: 0.000000
82
+ 2023-10-27 17:25:31,827 epoch 1 - iter 2232/3726 - loss 0.89439809 - time (sec): 277.02 - samples/sec: 442.39 - lr: 0.000003 - momentum: 0.000000
83
+ 2023-10-27 17:26:17,786 epoch 1 - iter 2604/3726 - loss 0.78674618 - time (sec): 322.97 - samples/sec: 443.93 - lr: 0.000003 - momentum: 0.000000
84
+ 2023-10-27 17:27:04,447 epoch 1 - iter 2976/3726 - loss 0.70312379 - time (sec): 369.64 - samples/sec: 443.20 - lr: 0.000004 - momentum: 0.000000
85
+ 2023-10-27 17:27:50,340 epoch 1 - iter 3348/3726 - loss 0.63740018 - time (sec): 415.53 - samples/sec: 442.57 - lr: 0.000004 - momentum: 0.000000
86
+ 2023-10-27 17:28:36,141 epoch 1 - iter 3720/3726 - loss 0.58486957 - time (sec): 461.33 - samples/sec: 442.64 - lr: 0.000005 - momentum: 0.000000
87
+ 2023-10-27 17:28:36,887 ----------------------------------------------------------------------------------------------------
88
+ 2023-10-27 17:28:36,887 EPOCH 1 done: loss 0.5838 - lr: 0.000005
89
+ 2023-10-27 17:28:59,836 DEV : loss 0.08319637179374695 - f1-score (micro avg) 0.9362
90
+ 2023-10-27 17:28:59,887 saving best model
91
+ 2023-10-27 17:29:02,186 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-27 17:29:48,303 epoch 2 - iter 372/3726 - loss 0.11238039 - time (sec): 46.11 - samples/sec: 434.33 - lr: 0.000005 - momentum: 0.000000
93
+ 2023-10-27 17:30:34,246 epoch 2 - iter 744/3726 - loss 0.10205120 - time (sec): 92.06 - samples/sec: 440.16 - lr: 0.000005 - momentum: 0.000000
94
+ 2023-10-27 17:31:20,589 epoch 2 - iter 1116/3726 - loss 0.09058251 - time (sec): 138.40 - samples/sec: 447.87 - lr: 0.000005 - momentum: 0.000000
95
+ 2023-10-27 17:32:06,506 epoch 2 - iter 1488/3726 - loss 0.09156566 - time (sec): 184.32 - samples/sec: 443.90 - lr: 0.000005 - momentum: 0.000000
96
+ 2023-10-27 17:32:52,277 epoch 2 - iter 1860/3726 - loss 0.08901480 - time (sec): 230.09 - samples/sec: 444.10 - lr: 0.000005 - momentum: 0.000000
97
+ 2023-10-27 17:33:38,125 epoch 2 - iter 2232/3726 - loss 0.08767046 - time (sec): 275.94 - samples/sec: 440.49 - lr: 0.000005 - momentum: 0.000000
98
+ 2023-10-27 17:34:23,826 epoch 2 - iter 2604/3726 - loss 0.08532145 - time (sec): 321.64 - samples/sec: 441.24 - lr: 0.000005 - momentum: 0.000000
99
+ 2023-10-27 17:35:09,960 epoch 2 - iter 2976/3726 - loss 0.08526503 - time (sec): 367.77 - samples/sec: 442.87 - lr: 0.000005 - momentum: 0.000000
100
+ 2023-10-27 17:35:56,636 epoch 2 - iter 3348/3726 - loss 0.08368925 - time (sec): 414.45 - samples/sec: 443.20 - lr: 0.000005 - momentum: 0.000000
101
+ 2023-10-27 17:36:42,804 epoch 2 - iter 3720/3726 - loss 0.08396268 - time (sec): 460.62 - samples/sec: 443.41 - lr: 0.000004 - momentum: 0.000000
102
+ 2023-10-27 17:36:43,519 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-27 17:36:43,519 EPOCH 2 done: loss 0.0838 - lr: 0.000004
104
+ 2023-10-27 17:37:07,571 DEV : loss 0.06706252694129944 - f1-score (micro avg) 0.9574
105
+ 2023-10-27 17:37:07,624 saving best model
106
+ 2023-10-27 17:37:10,584 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-27 17:37:57,573 epoch 3 - iter 372/3726 - loss 0.04814695 - time (sec): 46.99 - samples/sec: 438.53 - lr: 0.000004 - momentum: 0.000000
108
+ 2023-10-27 17:38:44,337 epoch 3 - iter 744/3726 - loss 0.04886821 - time (sec): 93.75 - samples/sec: 438.14 - lr: 0.000004 - momentum: 0.000000
109
+ 2023-10-27 17:39:31,726 epoch 3 - iter 1116/3726 - loss 0.05014060 - time (sec): 141.14 - samples/sec: 435.62 - lr: 0.000004 - momentum: 0.000000
110
+ 2023-10-27 17:40:18,792 epoch 3 - iter 1488/3726 - loss 0.05220008 - time (sec): 188.21 - samples/sec: 437.54 - lr: 0.000004 - momentum: 0.000000
111
+ 2023-10-27 17:41:05,149 epoch 3 - iter 1860/3726 - loss 0.05148240 - time (sec): 234.56 - samples/sec: 437.23 - lr: 0.000004 - momentum: 0.000000
112
+ 2023-10-27 17:41:52,025 epoch 3 - iter 2232/3726 - loss 0.05339505 - time (sec): 281.44 - samples/sec: 437.28 - lr: 0.000004 - momentum: 0.000000
113
+ 2023-10-27 17:42:38,711 epoch 3 - iter 2604/3726 - loss 0.05374593 - time (sec): 328.12 - samples/sec: 438.62 - lr: 0.000004 - momentum: 0.000000
114
+ 2023-10-27 17:43:25,619 epoch 3 - iter 2976/3726 - loss 0.05287703 - time (sec): 375.03 - samples/sec: 437.97 - lr: 0.000004 - momentum: 0.000000
115
+ 2023-10-27 17:44:13,432 epoch 3 - iter 3348/3726 - loss 0.05256041 - time (sec): 422.85 - samples/sec: 435.76 - lr: 0.000004 - momentum: 0.000000
116
+ 2023-10-27 17:45:00,348 epoch 3 - iter 3720/3726 - loss 0.05257701 - time (sec): 469.76 - samples/sec: 434.99 - lr: 0.000004 - momentum: 0.000000
117
+ 2023-10-27 17:45:01,081 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-27 17:45:01,082 EPOCH 3 done: loss 0.0526 - lr: 0.000004
119
+ 2023-10-27 17:45:25,642 DEV : loss 0.04900110512971878 - f1-score (micro avg) 0.9632
120
+ 2023-10-27 17:45:25,698 saving best model
121
+ 2023-10-27 17:45:28,617 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-27 17:46:15,914 epoch 4 - iter 372/3726 - loss 0.03649343 - time (sec): 47.29 - samples/sec: 421.21 - lr: 0.000004 - momentum: 0.000000
123
+ 2023-10-27 17:47:02,348 epoch 4 - iter 744/3726 - loss 0.03904655 - time (sec): 93.73 - samples/sec: 428.89 - lr: 0.000004 - momentum: 0.000000
124
+ 2023-10-27 17:47:50,016 epoch 4 - iter 1116/3726 - loss 0.03747173 - time (sec): 141.40 - samples/sec: 431.76 - lr: 0.000004 - momentum: 0.000000
125
+ 2023-10-27 17:48:37,609 epoch 4 - iter 1488/3726 - loss 0.03962095 - time (sec): 188.99 - samples/sec: 432.03 - lr: 0.000004 - momentum: 0.000000
126
+ 2023-10-27 17:49:24,478 epoch 4 - iter 1860/3726 - loss 0.03665861 - time (sec): 235.86 - samples/sec: 435.26 - lr: 0.000004 - momentum: 0.000000
127
+ 2023-10-27 17:50:10,615 epoch 4 - iter 2232/3726 - loss 0.03744683 - time (sec): 282.00 - samples/sec: 436.00 - lr: 0.000004 - momentum: 0.000000
128
+ 2023-10-27 17:50:56,634 epoch 4 - iter 2604/3726 - loss 0.03718038 - time (sec): 328.01 - samples/sec: 438.31 - lr: 0.000004 - momentum: 0.000000
129
+ 2023-10-27 17:51:41,898 epoch 4 - iter 2976/3726 - loss 0.03558423 - time (sec): 373.28 - samples/sec: 440.32 - lr: 0.000003 - momentum: 0.000000
130
+ 2023-10-27 17:52:27,923 epoch 4 - iter 3348/3726 - loss 0.03562024 - time (sec): 419.30 - samples/sec: 439.49 - lr: 0.000003 - momentum: 0.000000
131
+ 2023-10-27 17:53:14,720 epoch 4 - iter 3720/3726 - loss 0.03527266 - time (sec): 466.10 - samples/sec: 438.45 - lr: 0.000003 - momentum: 0.000000
132
+ 2023-10-27 17:53:15,487 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-27 17:53:15,487 EPOCH 4 done: loss 0.0353 - lr: 0.000003
134
+ 2023-10-27 17:53:38,247 DEV : loss 0.05077873915433884 - f1-score (micro avg) 0.9689
135
+ 2023-10-27 17:53:38,300 saving best model
136
+ 2023-10-27 17:53:41,578 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-27 17:54:28,406 epoch 5 - iter 372/3726 - loss 0.01635597 - time (sec): 46.83 - samples/sec: 431.15 - lr: 0.000003 - momentum: 0.000000
138
+ 2023-10-27 17:55:14,040 epoch 5 - iter 744/3726 - loss 0.01995793 - time (sec): 92.46 - samples/sec: 438.55 - lr: 0.000003 - momentum: 0.000000
139
+ 2023-10-27 17:56:00,008 epoch 5 - iter 1116/3726 - loss 0.02271135 - time (sec): 138.43 - samples/sec: 439.48 - lr: 0.000003 - momentum: 0.000000
140
+ 2023-10-27 17:56:46,029 epoch 5 - iter 1488/3726 - loss 0.02370028 - time (sec): 184.45 - samples/sec: 439.76 - lr: 0.000003 - momentum: 0.000000
141
+ 2023-10-27 17:57:32,057 epoch 5 - iter 1860/3726 - loss 0.02496095 - time (sec): 230.48 - samples/sec: 437.98 - lr: 0.000003 - momentum: 0.000000
142
+ 2023-10-27 17:58:18,548 epoch 5 - iter 2232/3726 - loss 0.02420606 - time (sec): 276.97 - samples/sec: 436.18 - lr: 0.000003 - momentum: 0.000000
143
+ 2023-10-27 17:59:05,818 epoch 5 - iter 2604/3726 - loss 0.02385058 - time (sec): 324.24 - samples/sec: 438.78 - lr: 0.000003 - momentum: 0.000000
144
+ 2023-10-27 17:59:52,270 epoch 5 - iter 2976/3726 - loss 0.02471771 - time (sec): 370.69 - samples/sec: 439.50 - lr: 0.000003 - momentum: 0.000000
145
+ 2023-10-27 18:00:39,106 epoch 5 - iter 3348/3726 - loss 0.02672304 - time (sec): 417.53 - samples/sec: 440.28 - lr: 0.000003 - momentum: 0.000000
146
+ 2023-10-27 18:01:25,971 epoch 5 - iter 3720/3726 - loss 0.02642411 - time (sec): 464.39 - samples/sec: 439.82 - lr: 0.000003 - momentum: 0.000000
147
+ 2023-10-27 18:01:26,740 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-27 18:01:26,740 EPOCH 5 done: loss 0.0264 - lr: 0.000003
149
+ 2023-10-27 18:01:50,293 DEV : loss 0.05235698074102402 - f1-score (micro avg) 0.972
150
+ 2023-10-27 18:01:50,346 saving best model
151
+ 2023-10-27 18:01:53,254 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-27 18:02:39,752 epoch 6 - iter 372/3726 - loss 0.02916463 - time (sec): 46.49 - samples/sec: 446.96 - lr: 0.000003 - momentum: 0.000000
153
+ 2023-10-27 18:03:25,626 epoch 6 - iter 744/3726 - loss 0.02452630 - time (sec): 92.37 - samples/sec: 442.98 - lr: 0.000003 - momentum: 0.000000
154
+ 2023-10-27 18:04:11,837 epoch 6 - iter 1116/3726 - loss 0.02460461 - time (sec): 138.58 - samples/sec: 443.92 - lr: 0.000003 - momentum: 0.000000
155
+ 2023-10-27 18:04:59,229 epoch 6 - iter 1488/3726 - loss 0.02344474 - time (sec): 185.97 - samples/sec: 441.02 - lr: 0.000003 - momentum: 0.000000
156
+ 2023-10-27 18:05:46,701 epoch 6 - iter 1860/3726 - loss 0.02371111 - time (sec): 233.44 - samples/sec: 438.96 - lr: 0.000003 - momentum: 0.000000
157
+ 2023-10-27 18:06:33,625 epoch 6 - iter 2232/3726 - loss 0.02288733 - time (sec): 280.37 - samples/sec: 438.13 - lr: 0.000002 - momentum: 0.000000
158
+ 2023-10-27 18:07:19,620 epoch 6 - iter 2604/3726 - loss 0.02107152 - time (sec): 326.36 - samples/sec: 438.12 - lr: 0.000002 - momentum: 0.000000
159
+ 2023-10-27 18:08:06,623 epoch 6 - iter 2976/3726 - loss 0.02064455 - time (sec): 373.36 - samples/sec: 437.04 - lr: 0.000002 - momentum: 0.000000
160
+ 2023-10-27 18:08:52,249 epoch 6 - iter 3348/3726 - loss 0.02103691 - time (sec): 418.99 - samples/sec: 438.95 - lr: 0.000002 - momentum: 0.000000
161
+ 2023-10-27 18:09:38,374 epoch 6 - iter 3720/3726 - loss 0.02102916 - time (sec): 465.12 - samples/sec: 439.25 - lr: 0.000002 - momentum: 0.000000
162
+ 2023-10-27 18:09:39,127 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-27 18:09:39,128 EPOCH 6 done: loss 0.0211 - lr: 0.000002
164
+ 2023-10-27 18:10:02,947 DEV : loss 0.05808666720986366 - f1-score (micro avg) 0.9682
165
+ 2023-10-27 18:10:03,000 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-27 18:10:49,637 epoch 7 - iter 372/3726 - loss 0.01575730 - time (sec): 46.63 - samples/sec: 435.88 - lr: 0.000002 - momentum: 0.000000
167
+ 2023-10-27 18:11:35,967 epoch 7 - iter 744/3726 - loss 0.01398724 - time (sec): 92.96 - samples/sec: 438.00 - lr: 0.000002 - momentum: 0.000000
168
+ 2023-10-27 18:12:22,831 epoch 7 - iter 1116/3726 - loss 0.01313005 - time (sec): 139.83 - samples/sec: 442.95 - lr: 0.000002 - momentum: 0.000000
169
+ 2023-10-27 18:13:08,773 epoch 7 - iter 1488/3726 - loss 0.01291165 - time (sec): 185.77 - samples/sec: 443.62 - lr: 0.000002 - momentum: 0.000000
170
+ 2023-10-27 18:13:54,815 epoch 7 - iter 1860/3726 - loss 0.01295979 - time (sec): 231.81 - samples/sec: 441.98 - lr: 0.000002 - momentum: 0.000000
171
+ 2023-10-27 18:14:40,721 epoch 7 - iter 2232/3726 - loss 0.01255139 - time (sec): 277.72 - samples/sec: 442.13 - lr: 0.000002 - momentum: 0.000000
172
+ 2023-10-27 18:15:28,159 epoch 7 - iter 2604/3726 - loss 0.01200459 - time (sec): 325.16 - samples/sec: 439.39 - lr: 0.000002 - momentum: 0.000000
173
+ 2023-10-27 18:16:14,038 epoch 7 - iter 2976/3726 - loss 0.01248980 - time (sec): 371.04 - samples/sec: 440.26 - lr: 0.000002 - momentum: 0.000000
174
+ 2023-10-27 18:16:59,656 epoch 7 - iter 3348/3726 - loss 0.01321463 - time (sec): 416.65 - samples/sec: 441.16 - lr: 0.000002 - momentum: 0.000000
175
+ 2023-10-27 18:17:45,100 epoch 7 - iter 3720/3726 - loss 0.01382182 - time (sec): 462.10 - samples/sec: 442.14 - lr: 0.000002 - momentum: 0.000000
176
+ 2023-10-27 18:17:45,799 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-27 18:17:45,800 EPOCH 7 done: loss 0.0138 - lr: 0.000002
178
+ 2023-10-27 18:18:08,992 DEV : loss 0.058880679309368134 - f1-score (micro avg) 0.9703
179
+ 2023-10-27 18:18:09,048 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-27 18:18:55,063 epoch 8 - iter 372/3726 - loss 0.01490756 - time (sec): 46.01 - samples/sec: 448.34 - lr: 0.000002 - momentum: 0.000000
181
+ 2023-10-27 18:19:41,086 epoch 8 - iter 744/3726 - loss 0.01079045 - time (sec): 92.03 - samples/sec: 439.19 - lr: 0.000002 - momentum: 0.000000
182
+ 2023-10-27 18:20:27,084 epoch 8 - iter 1116/3726 - loss 0.01191125 - time (sec): 138.03 - samples/sec: 443.50 - lr: 0.000002 - momentum: 0.000000
183
+ 2023-10-27 18:21:12,462 epoch 8 - iter 1488/3726 - loss 0.01100526 - time (sec): 183.41 - samples/sec: 451.17 - lr: 0.000001 - momentum: 0.000000
184
+ 2023-10-27 18:21:58,283 epoch 8 - iter 1860/3726 - loss 0.01185326 - time (sec): 229.23 - samples/sec: 448.88 - lr: 0.000001 - momentum: 0.000000
185
+ 2023-10-27 18:22:44,335 epoch 8 - iter 2232/3726 - loss 0.01176460 - time (sec): 275.28 - samples/sec: 445.95 - lr: 0.000001 - momentum: 0.000000
186
+ 2023-10-27 18:23:30,785 epoch 8 - iter 2604/3726 - loss 0.01194894 - time (sec): 321.73 - samples/sec: 442.88 - lr: 0.000001 - momentum: 0.000000
187
+ 2023-10-27 18:24:17,599 epoch 8 - iter 2976/3726 - loss 0.01190633 - time (sec): 368.55 - samples/sec: 441.32 - lr: 0.000001 - momentum: 0.000000
188
+ 2023-10-27 18:25:04,773 epoch 8 - iter 3348/3726 - loss 0.01189745 - time (sec): 415.72 - samples/sec: 441.59 - lr: 0.000001 - momentum: 0.000000
189
+ 2023-10-27 18:25:51,526 epoch 8 - iter 3720/3726 - loss 0.01191728 - time (sec): 462.48 - samples/sec: 441.51 - lr: 0.000001 - momentum: 0.000000
190
+ 2023-10-27 18:25:52,333 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-27 18:25:52,333 EPOCH 8 done: loss 0.0120 - lr: 0.000001
192
+ 2023-10-27 18:26:16,427 DEV : loss 0.05278489366173744 - f1-score (micro avg) 0.9741
193
+ 2023-10-27 18:26:16,480 saving best model
194
+ 2023-10-27 18:26:19,470 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-27 18:27:05,544 epoch 9 - iter 372/3726 - loss 0.00965068 - time (sec): 46.07 - samples/sec: 441.62 - lr: 0.000001 - momentum: 0.000000
196
+ 2023-10-27 18:27:51,054 epoch 9 - iter 744/3726 - loss 0.00782923 - time (sec): 91.58 - samples/sec: 445.46 - lr: 0.000001 - momentum: 0.000000
197
+ 2023-10-27 18:28:36,410 epoch 9 - iter 1116/3726 - loss 0.00714565 - time (sec): 136.94 - samples/sec: 450.28 - lr: 0.000001 - momentum: 0.000000
198
+ 2023-10-27 18:29:22,141 epoch 9 - iter 1488/3726 - loss 0.00788002 - time (sec): 182.67 - samples/sec: 451.72 - lr: 0.000001 - momentum: 0.000000
199
+ 2023-10-27 18:30:08,759 epoch 9 - iter 1860/3726 - loss 0.00817722 - time (sec): 229.29 - samples/sec: 448.24 - lr: 0.000001 - momentum: 0.000000
200
+ 2023-10-27 18:30:54,418 epoch 9 - iter 2232/3726 - loss 0.00812347 - time (sec): 274.95 - samples/sec: 446.63 - lr: 0.000001 - momentum: 0.000000
201
+ 2023-10-27 18:31:40,019 epoch 9 - iter 2604/3726 - loss 0.00818017 - time (sec): 320.55 - samples/sec: 446.97 - lr: 0.000001 - momentum: 0.000000
202
+ 2023-10-27 18:32:25,812 epoch 9 - iter 2976/3726 - loss 0.00800987 - time (sec): 366.34 - samples/sec: 445.32 - lr: 0.000001 - momentum: 0.000000
203
+ 2023-10-27 18:33:11,863 epoch 9 - iter 3348/3726 - loss 0.00815904 - time (sec): 412.39 - samples/sec: 445.22 - lr: 0.000001 - momentum: 0.000000
204
+ 2023-10-27 18:33:57,717 epoch 9 - iter 3720/3726 - loss 0.00780421 - time (sec): 458.24 - samples/sec: 445.83 - lr: 0.000001 - momentum: 0.000000
205
+ 2023-10-27 18:33:58,426 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-27 18:33:58,426 EPOCH 9 done: loss 0.0078 - lr: 0.000001
207
+ 2023-10-27 18:34:21,819 DEV : loss 0.05219843238592148 - f1-score (micro avg) 0.9766
208
+ 2023-10-27 18:34:21,872 saving best model
209
+ 2023-10-27 18:34:24,714 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-27 18:35:10,773 epoch 10 - iter 372/3726 - loss 0.00735364 - time (sec): 46.06 - samples/sec: 439.89 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-27 18:35:55,957 epoch 10 - iter 744/3726 - loss 0.00724933 - time (sec): 91.24 - samples/sec: 448.71 - lr: 0.000000 - momentum: 0.000000
212
+ 2023-10-27 18:36:41,613 epoch 10 - iter 1116/3726 - loss 0.00540230 - time (sec): 136.90 - samples/sec: 451.22 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-27 18:37:26,965 epoch 10 - iter 1488/3726 - loss 0.00604023 - time (sec): 182.25 - samples/sec: 453.12 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-27 18:38:12,558 epoch 10 - iter 1860/3726 - loss 0.00646998 - time (sec): 227.84 - samples/sec: 452.95 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-27 18:38:58,762 epoch 10 - iter 2232/3726 - loss 0.00621628 - time (sec): 274.05 - samples/sec: 449.84 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-27 18:39:45,050 epoch 10 - iter 2604/3726 - loss 0.00611127 - time (sec): 320.33 - samples/sec: 447.82 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-27 18:40:30,686 epoch 10 - iter 2976/3726 - loss 0.00609183 - time (sec): 365.97 - samples/sec: 447.92 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-27 18:41:16,049 epoch 10 - iter 3348/3726 - loss 0.00601238 - time (sec): 411.33 - samples/sec: 447.77 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-27 18:42:01,610 epoch 10 - iter 3720/3726 - loss 0.00601111 - time (sec): 456.89 - samples/sec: 447.20 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-27 18:42:02,342 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-27 18:42:02,343 EPOCH 10 done: loss 0.0060 - lr: 0.000000
222
+ 2023-10-27 18:42:25,659 DEV : loss 0.05048835650086403 - f1-score (micro avg) 0.9762
223
+ 2023-10-27 18:42:28,164 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-27 18:42:28,165 Loading model from best epoch ...
225
+ 2023-10-27 18:42:36,107 SequenceTagger predicts: Dictionary with 17 tags: O, S-ORG, B-ORG, E-ORG, I-ORG, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-MISC, B-MISC, E-MISC, I-MISC
226
+ 2023-10-27 18:42:59,035
227
+ Results:
228
+ - F-score (micro) 0.9702
229
+ - F-score (macro) 0.9649
230
+ - Accuracy 0.956
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ ORG 0.9623 0.9749 0.9685 1909
236
+ PER 0.9962 0.9950 0.9956 1591
237
+ LOC 0.9729 0.9660 0.9695 1413
238
+ MISC 0.9178 0.9347 0.9262 812
239
+
240
+ micro avg 0.9678 0.9726 0.9702 5725
241
+ macro avg 0.9623 0.9676 0.9649 5725
242
+ weighted avg 0.9680 0.9726 0.9703 5725
243
+
244
+ 2023-10-27 18:42:59,036 ----------------------------------------------------------------------------------------------------