Hugging Face's logo

stefan-it
/
flair-clean-conll-1

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
hetzner
hetzner-gex44
hetzner-gpu
Model card Files Metrics Community
stefan-it commited on
Commit
dd1dfcd
•
1 Parent(s): 0d27414

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 14:30:09,020 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-27 14:30:09,022 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 14:30:09,022 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-27 14:30:09,022 Corpus: 14903 train + 3449 dev + 3658 test sentences
52
+ 2023-10-27 14:30:09,022 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-27 14:30:09,022 Train: 14903 sentences
54
+ 2023-10-27 14:30:09,022 (train_with_dev=False, train_with_test=False)
55
+ 2023-10-27 14:30:09,022 ----------------------------------------------------------------------------------------------------
56
+ 2023-10-27 14:30:09,022 Training Params:
57
+ 2023-10-27 14:30:09,022 - learning_rate: "5e-06"
58
+ 2023-10-27 14:30:09,022 - mini_batch_size: "4"
59
+ 2023-10-27 14:30:09,022 - max_epochs: "10"
60
+ 2023-10-27 14:30:09,022 - shuffle: "True"
61
+ 2023-10-27 14:30:09,022 ----------------------------------------------------------------------------------------------------
62
+ 2023-10-27 14:30:09,022 Plugins:
63
+ 2023-10-27 14:30:09,022 - TensorboardLogger
64
+ 2023-10-27 14:30:09,022 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-27 14:30:09,022 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-27 14:30:09,022 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-27 14:30:09,023 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-27 14:30:09,023 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-27 14:30:09,023 Computation:
70
+ 2023-10-27 14:30:09,023 - compute on device: cuda:0
71
+ 2023-10-27 14:30:09,023 - embedding storage: none
72
+ 2023-10-27 14:30:09,023 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-27 14:30:09,023 Model training base path: "flair-clean-conll-lr5e-06-bs4-1"
74
+ 2023-10-27 14:30:09,023 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-27 14:30:09,023 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-27 14:30:09,023 Logging anything other than scalars to TensorBoard is currently not supported.
77
+ 2023-10-27 14:31:00,447 epoch 1 - iter 372/3726 - loss 3.59658936 - time (sec): 51.42 - samples/sec: 413.36 - lr: 0.000000 - momentum: 0.000000
78
+ 2023-10-27 14:31:51,041 epoch 1 - iter 744/3726 - loss 2.26388470 - time (sec): 102.02 - samples/sec: 413.01 - lr: 0.000001 - momentum: 0.000000
79
+ 2023-10-27 14:32:42,079 epoch 1 - iter 1116/3726 - loss 1.71280298 - time (sec): 153.05 - samples/sec: 407.18 - lr: 0.000001 - momentum: 0.000000
80
+ 2023-10-27 14:33:32,757 epoch 1 - iter 1488/3726 - loss 1.39694066 - time (sec): 203.73 - samples/sec: 405.85 - lr: 0.000002 - momentum: 0.000000
81
+ 2023-10-27 14:34:23,303 epoch 1 - iter 1860/3726 - loss 1.17731325 - time (sec): 254.28 - samples/sec: 406.61 - lr: 0.000002 - momentum: 0.000000
82
+ 2023-10-27 14:35:13,791 epoch 1 - iter 2232/3726 - loss 1.01805377 - time (sec): 304.77 - samples/sec: 405.77 - lr: 0.000003 - momentum: 0.000000
83
+ 2023-10-27 14:36:04,555 epoch 1 - iter 2604/3726 - loss 0.89618095 - time (sec): 355.53 - samples/sec: 404.90 - lr: 0.000003 - momentum: 0.000000
84
+ 2023-10-27 14:36:55,602 epoch 1 - iter 2976/3726 - loss 0.80113668 - time (sec): 406.58 - samples/sec: 403.81 - lr: 0.000004 - momentum: 0.000000
85
+ 2023-10-27 14:37:46,433 epoch 1 - iter 3348/3726 - loss 0.72868926 - time (sec): 457.41 - samples/sec: 401.79 - lr: 0.000004 - momentum: 0.000000
86
+ 2023-10-27 14:38:36,663 epoch 1 - iter 3720/3726 - loss 0.66657776 - time (sec): 507.64 - samples/sec: 402.50 - lr: 0.000005 - momentum: 0.000000
87
+ 2023-10-27 14:38:37,488 ----------------------------------------------------------------------------------------------------
88
+ 2023-10-27 14:38:37,488 EPOCH 1 done: loss 0.6659 - lr: 0.000005
89
+ 2023-10-27 14:39:02,791 DEV : loss 0.0933869257569313 - f1-score (micro avg) 0.9262
90
+ 2023-10-27 14:39:02,853 saving best model
91
+ 2023-10-27 14:39:05,885 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-27 14:39:56,330 epoch 2 - iter 372/3726 - loss 0.09283601 - time (sec): 50.44 - samples/sec: 393.59 - lr: 0.000005 - momentum: 0.000000
93
+ 2023-10-27 14:40:47,261 epoch 2 - iter 744/3726 - loss 0.08756607 - time (sec): 101.37 - samples/sec: 396.30 - lr: 0.000005 - momentum: 0.000000
94
+ 2023-10-27 14:41:38,098 epoch 2 - iter 1116/3726 - loss 0.08583083 - time (sec): 152.21 - samples/sec: 397.99 - lr: 0.000005 - momentum: 0.000000
95
+ 2023-10-27 14:42:28,471 epoch 2 - iter 1488/3726 - loss 0.08370769 - time (sec): 202.58 - samples/sec: 400.87 - lr: 0.000005 - momentum: 0.000000
96
+ 2023-10-27 14:43:19,871 epoch 2 - iter 1860/3726 - loss 0.08404411 - time (sec): 253.98 - samples/sec: 399.49 - lr: 0.000005 - momentum: 0.000000
97
+ 2023-10-27 14:44:10,168 epoch 2 - iter 2232/3726 - loss 0.08124313 - time (sec): 304.28 - samples/sec: 397.73 - lr: 0.000005 - momentum: 0.000000
98
+ 2023-10-27 14:45:01,496 epoch 2 - iter 2604/3726 - loss 0.08228873 - time (sec): 355.61 - samples/sec: 397.75 - lr: 0.000005 - momentum: 0.000000
99
+ 2023-10-27 14:45:52,335 epoch 2 - iter 2976/3726 - loss 0.08159191 - time (sec): 406.45 - samples/sec: 399.36 - lr: 0.000005 - momentum: 0.000000
100
+ 2023-10-27 14:46:43,142 epoch 2 - iter 3348/3726 - loss 0.08066519 - time (sec): 457.26 - samples/sec: 401.12 - lr: 0.000005 - momentum: 0.000000
101
+ 2023-10-27 14:47:34,049 epoch 2 - iter 3720/3726 - loss 0.08043171 - time (sec): 508.16 - samples/sec: 402.15 - lr: 0.000004 - momentum: 0.000000
102
+ 2023-10-27 14:47:34,866 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-27 14:47:34,866 EPOCH 2 done: loss 0.0805 - lr: 0.000004
104
+ 2023-10-27 14:48:01,712 DEV : loss 0.06152888387441635 - f1-score (micro avg) 0.9481
105
+ 2023-10-27 14:48:01,789 saving best model
106
+ 2023-10-27 14:48:05,294 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-27 14:48:55,650 epoch 3 - iter 372/3726 - loss 0.06085669 - time (sec): 50.35 - samples/sec: 406.39 - lr: 0.000004 - momentum: 0.000000
108
+ 2023-10-27 14:49:46,492 epoch 3 - iter 744/3726 - loss 0.05743897 - time (sec): 101.20 - samples/sec: 400.38 - lr: 0.000004 - momentum: 0.000000
109
+ 2023-10-27 14:50:36,994 epoch 3 - iter 1116/3726 - loss 0.05779768 - time (sec): 151.70 - samples/sec: 398.09 - lr: 0.000004 - momentum: 0.000000
110
+ 2023-10-27 14:51:26,995 epoch 3 - iter 1488/3726 - loss 0.05644504 - time (sec): 201.70 - samples/sec: 401.46 - lr: 0.000004 - momentum: 0.000000
111
+ 2023-10-27 14:52:17,584 epoch 3 - iter 1860/3726 - loss 0.05572416 - time (sec): 252.29 - samples/sec: 403.62 - lr: 0.000004 - momentum: 0.000000
112
+ 2023-10-27 14:53:08,570 epoch 3 - iter 2232/3726 - loss 0.05352112 - time (sec): 303.27 - samples/sec: 403.61 - lr: 0.000004 - momentum: 0.000000
113
+ 2023-10-27 14:53:59,036 epoch 3 - iter 2604/3726 - loss 0.05461713 - time (sec): 353.74 - samples/sec: 404.61 - lr: 0.000004 - momentum: 0.000000
114
+ 2023-10-27 14:54:49,877 epoch 3 - iter 2976/3726 - loss 0.05390525 - time (sec): 404.58 - samples/sec: 405.62 - lr: 0.000004 - momentum: 0.000000
115
+ 2023-10-27 14:55:41,535 epoch 3 - iter 3348/3726 - loss 0.05442763 - time (sec): 456.24 - samples/sec: 402.73 - lr: 0.000004 - momentum: 0.000000
116
+ 2023-10-27 14:56:32,799 epoch 3 - iter 3720/3726 - loss 0.05458475 - time (sec): 507.50 - samples/sec: 402.71 - lr: 0.000004 - momentum: 0.000000
117
+ 2023-10-27 14:56:33,616 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-27 14:56:33,617 EPOCH 3 done: loss 0.0545 - lr: 0.000004
119
+ 2023-10-27 14:57:00,329 DEV : loss 0.06314758211374283 - f1-score (micro avg) 0.9612
120
+ 2023-10-27 14:57:00,411 saving best model
121
+ 2023-10-27 14:57:03,863 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-27 14:57:54,121 epoch 4 - iter 372/3726 - loss 0.03226694 - time (sec): 50.26 - samples/sec: 411.62 - lr: 0.000004 - momentum: 0.000000
123
+ 2023-10-27 14:58:44,919 epoch 4 - iter 744/3726 - loss 0.03936813 - time (sec): 101.05 - samples/sec: 405.68 - lr: 0.000004 - momentum: 0.000000
124
+ 2023-10-27 14:59:35,509 epoch 4 - iter 1116/3726 - loss 0.03970607 - time (sec): 151.64 - samples/sec: 406.37 - lr: 0.000004 - momentum: 0.000000
125
+ 2023-10-27 15:00:23,759 epoch 4 - iter 1488/3726 - loss 0.04029682 - time (sec): 199.89 - samples/sec: 408.57 - lr: 0.000004 - momentum: 0.000000
126
+ 2023-10-27 15:01:12,178 epoch 4 - iter 1860/3726 - loss 0.03993881 - time (sec): 248.31 - samples/sec: 412.03 - lr: 0.000004 - momentum: 0.000000
127
+ 2023-10-27 15:01:59,669 epoch 4 - iter 2232/3726 - loss 0.03825023 - time (sec): 295.80 - samples/sec: 415.38 - lr: 0.000004 - momentum: 0.000000
128
+ 2023-10-27 15:02:46,739 epoch 4 - iter 2604/3726 - loss 0.03860270 - time (sec): 342.87 - samples/sec: 417.88 - lr: 0.000004 - momentum: 0.000000
129
+ 2023-10-27 15:03:33,155 epoch 4 - iter 2976/3726 - loss 0.03883180 - time (sec): 389.29 - samples/sec: 420.36 - lr: 0.000003 - momentum: 0.000000
130
+ 2023-10-27 15:04:18,906 epoch 4 - iter 3348/3726 - loss 0.03843582 - time (sec): 435.04 - samples/sec: 424.15 - lr: 0.000003 - momentum: 0.000000
131
+ 2023-10-27 15:05:06,069 epoch 4 - iter 3720/3726 - loss 0.03900868 - time (sec): 482.20 - samples/sec: 423.76 - lr: 0.000003 - momentum: 0.000000
132
+ 2023-10-27 15:05:06,804 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-27 15:05:06,805 EPOCH 4 done: loss 0.0390 - lr: 0.000003
134
+ 2023-10-27 15:05:31,408 DEV : loss 0.04959763213992119 - f1-score (micro avg) 0.9678
135
+ 2023-10-27 15:05:31,469 saving best model
136
+ 2023-10-27 15:05:34,206 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-27 15:06:22,854 epoch 5 - iter 372/3726 - loss 0.02632753 - time (sec): 48.65 - samples/sec: 413.87 - lr: 0.000003 - momentum: 0.000000
138
+ 2023-10-27 15:07:09,362 epoch 5 - iter 744/3726 - loss 0.02847207 - time (sec): 95.15 - samples/sec: 431.29 - lr: 0.000003 - momentum: 0.000000
139
+ 2023-10-27 15:07:56,415 epoch 5 - iter 1116/3726 - loss 0.02792443 - time (sec): 142.21 - samples/sec: 432.32 - lr: 0.000003 - momentum: 0.000000
140
+ 2023-10-27 15:08:43,809 epoch 5 - iter 1488/3726 - loss 0.02808337 - time (sec): 189.60 - samples/sec: 432.27 - lr: 0.000003 - momentum: 0.000000
141
+ 2023-10-27 15:09:32,174 epoch 5 - iter 1860/3726 - loss 0.02852601 - time (sec): 237.97 - samples/sec: 426.16 - lr: 0.000003 - momentum: 0.000000
142
+ 2023-10-27 15:10:19,545 epoch 5 - iter 2232/3726 - loss 0.02859382 - time (sec): 285.34 - samples/sec: 427.84 - lr: 0.000003 - momentum: 0.000000
143
+ 2023-10-27 15:11:08,221 epoch 5 - iter 2604/3726 - loss 0.02812313 - time (sec): 334.01 - samples/sec: 426.57 - lr: 0.000003 - momentum: 0.000000
144
+ 2023-10-27 15:11:55,520 epoch 5 - iter 2976/3726 - loss 0.02819121 - time (sec): 381.31 - samples/sec: 427.48 - lr: 0.000003 - momentum: 0.000000
145
+ 2023-10-27 15:12:43,398 epoch 5 - iter 3348/3726 - loss 0.02832524 - time (sec): 429.19 - samples/sec: 426.98 - lr: 0.000003 - momentum: 0.000000
146
+ 2023-10-27 15:13:30,169 epoch 5 - iter 3720/3726 - loss 0.02864353 - time (sec): 475.96 - samples/sec: 429.13 - lr: 0.000003 - momentum: 0.000000
147
+ 2023-10-27 15:13:30,908 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-27 15:13:30,909 EPOCH 5 done: loss 0.0286 - lr: 0.000003
149
+ 2023-10-27 15:13:55,872 DEV : loss 0.051205169409513474 - f1-score (micro avg) 0.969
150
+ 2023-10-27 15:13:55,926 saving best model
151
+ 2023-10-27 15:13:58,971 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-27 15:14:46,203 epoch 6 - iter 372/3726 - loss 0.02831335 - time (sec): 47.23 - samples/sec: 428.83 - lr: 0.000003 - momentum: 0.000000
153
+ 2023-10-27 15:15:35,236 epoch 6 - iter 744/3726 - loss 0.02273400 - time (sec): 96.26 - samples/sec: 426.78 - lr: 0.000003 - momentum: 0.000000
154
+ 2023-10-27 15:16:23,193 epoch 6 - iter 1116/3726 - loss 0.02109002 - time (sec): 144.22 - samples/sec: 423.66 - lr: 0.000003 - momentum: 0.000000
155
+ 2023-10-27 15:17:10,302 epoch 6 - iter 1488/3726 - loss 0.02166135 - time (sec): 191.33 - samples/sec: 429.37 - lr: 0.000003 - momentum: 0.000000
156
+ 2023-10-27 15:17:58,889 epoch 6 - iter 1860/3726 - loss 0.02127214 - time (sec): 239.91 - samples/sec: 429.35 - lr: 0.000003 - momentum: 0.000000
157
+ 2023-10-27 15:18:45,994 epoch 6 - iter 2232/3726 - loss 0.02116817 - time (sec): 287.02 - samples/sec: 428.54 - lr: 0.000002 - momentum: 0.000000
158
+ 2023-10-27 15:19:34,532 epoch 6 - iter 2604/3726 - loss 0.02139499 - time (sec): 335.56 - samples/sec: 427.19 - lr: 0.000002 - momentum: 0.000000
159
+ 2023-10-27 15:20:22,599 epoch 6 - iter 2976/3726 - loss 0.02130084 - time (sec): 383.62 - samples/sec: 425.85 - lr: 0.000002 - momentum: 0.000000
160
+ 2023-10-27 15:21:10,024 epoch 6 - iter 3348/3726 - loss 0.02121915 - time (sec): 431.05 - samples/sec: 425.94 - lr: 0.000002 - momentum: 0.000000
161
+ 2023-10-27 15:21:57,177 epoch 6 - iter 3720/3726 - loss 0.02100853 - time (sec): 478.20 - samples/sec: 427.07 - lr: 0.000002 - momentum: 0.000000
162
+ 2023-10-27 15:21:57,964 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-27 15:21:57,964 EPOCH 6 done: loss 0.0210 - lr: 0.000002
164
+ 2023-10-27 15:22:23,206 DEV : loss 0.05652967095375061 - f1-score (micro avg) 0.9686
165
+ 2023-10-27 15:22:23,264 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-27 15:23:11,169 epoch 7 - iter 372/3726 - loss 0.01511217 - time (sec): 47.90 - samples/sec: 438.07 - lr: 0.000002 - momentum: 0.000000
167
+ 2023-10-27 15:23:58,577 epoch 7 - iter 744/3726 - loss 0.01678792 - time (sec): 95.31 - samples/sec: 441.01 - lr: 0.000002 - momentum: 0.000000
168
+ 2023-10-27 15:24:46,315 epoch 7 - iter 1116/3726 - loss 0.01767805 - time (sec): 143.05 - samples/sec: 436.03 - lr: 0.000002 - momentum: 0.000000
169
+ 2023-10-27 15:25:34,119 epoch 7 - iter 1488/3726 - loss 0.01634669 - time (sec): 190.85 - samples/sec: 434.79 - lr: 0.000002 - momentum: 0.000000
170
+ 2023-10-27 15:26:21,351 epoch 7 - iter 1860/3726 - loss 0.02015737 - time (sec): 238.08 - samples/sec: 437.30 - lr: 0.000002 - momentum: 0.000000
171
+ 2023-10-27 15:27:08,458 epoch 7 - iter 2232/3726 - loss 0.01895408 - time (sec): 285.19 - samples/sec: 435.98 - lr: 0.000002 - momentum: 0.000000
172
+ 2023-10-27 15:27:56,799 epoch 7 - iter 2604/3726 - loss 0.01784524 - time (sec): 333.53 - samples/sec: 433.67 - lr: 0.000002 - momentum: 0.000000
173
+ 2023-10-27 15:28:45,164 epoch 7 - iter 2976/3726 - loss 0.01736500 - time (sec): 381.90 - samples/sec: 431.20 - lr: 0.000002 - momentum: 0.000000
174
+ 2023-10-27 15:29:33,002 epoch 7 - iter 3348/3726 - loss 0.01709685 - time (sec): 429.74 - samples/sec: 429.19 - lr: 0.000002 - momentum: 0.000000
175
+ 2023-10-27 15:30:19,962 epoch 7 - iter 3720/3726 - loss 0.01680664 - time (sec): 476.70 - samples/sec: 428.73 - lr: 0.000002 - momentum: 0.000000
176
+ 2023-10-27 15:30:20,674 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-27 15:30:20,674 EPOCH 7 done: loss 0.0168 - lr: 0.000002
178
+ 2023-10-27 15:30:43,202 DEV : loss 0.052628789097070694 - f1-score (micro avg) 0.9722
179
+ 2023-10-27 15:30:43,260 saving best model
180
+ 2023-10-27 15:30:46,516 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-27 15:31:32,754 epoch 8 - iter 372/3726 - loss 0.01025399 - time (sec): 46.24 - samples/sec: 450.08 - lr: 0.000002 - momentum: 0.000000
182
+ 2023-10-27 15:32:18,558 epoch 8 - iter 744/3726 - loss 0.01126091 - time (sec): 92.04 - samples/sec: 447.34 - lr: 0.000002 - momentum: 0.000000
183
+ 2023-10-27 15:33:03,647 epoch 8 - iter 1116/3726 - loss 0.01172293 - time (sec): 137.13 - samples/sec: 445.99 - lr: 0.000002 - momentum: 0.000000
184
+ 2023-10-27 15:33:49,381 epoch 8 - iter 1488/3726 - loss 0.01219846 - time (sec): 182.86 - samples/sec: 440.90 - lr: 0.000001 - momentum: 0.000000
185
+ 2023-10-27 15:34:35,063 epoch 8 - iter 1860/3726 - loss 0.01190833 - time (sec): 228.55 - samples/sec: 443.89 - lr: 0.000001 - momentum: 0.000000
186
+ 2023-10-27 15:35:20,762 epoch 8 - iter 2232/3726 - loss 0.01209883 - time (sec): 274.24 - samples/sec: 442.06 - lr: 0.000001 - momentum: 0.000000
187
+ 2023-10-27 15:36:06,906 epoch 8 - iter 2604/3726 - loss 0.01227890 - time (sec): 320.39 - samples/sec: 442.88 - lr: 0.000001 - momentum: 0.000000
188
+ 2023-10-27 15:36:52,771 epoch 8 - iter 2976/3726 - loss 0.01220756 - time (sec): 366.25 - samples/sec: 444.61 - lr: 0.000001 - momentum: 0.000000
189
+ 2023-10-27 15:37:38,958 epoch 8 - iter 3348/3726 - loss 0.01181082 - time (sec): 412.44 - samples/sec: 446.10 - lr: 0.000001 - momentum: 0.000000
190
+ 2023-10-27 15:38:24,879 epoch 8 - iter 3720/3726 - loss 0.01141249 - time (sec): 458.36 - samples/sec: 445.64 - lr: 0.000001 - momentum: 0.000000
191
+ 2023-10-27 15:38:25,618 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-27 15:38:25,619 EPOCH 8 done: loss 0.0114 - lr: 0.000001
193
+ 2023-10-27 15:38:49,028 DEV : loss 0.053019002079963684 - f1-score (micro avg) 0.9716
194
+ 2023-10-27 15:38:49,088 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-27 15:39:35,150 epoch 9 - iter 372/3726 - loss 0.00801185 - time (sec): 46.06 - samples/sec: 438.23 - lr: 0.000001 - momentum: 0.000000
196
+ 2023-10-27 15:40:20,869 epoch 9 - iter 744/3726 - loss 0.00671566 - time (sec): 91.78 - samples/sec: 435.43 - lr: 0.000001 - momentum: 0.000000
197
+ 2023-10-27 15:41:07,081 epoch 9 - iter 1116/3726 - loss 0.00667937 - time (sec): 137.99 - samples/sec: 438.20 - lr: 0.000001 - momentum: 0.000000
198
+ 2023-10-27 15:41:53,955 epoch 9 - iter 1488/3726 - loss 0.00681524 - time (sec): 184.87 - samples/sec: 439.41 - lr: 0.000001 - momentum: 0.000000
199
+ 2023-10-27 15:42:41,635 epoch 9 - iter 1860/3726 - loss 0.00721784 - time (sec): 232.55 - samples/sec: 437.37 - lr: 0.000001 - momentum: 0.000000
200
+ 2023-10-27 15:43:28,277 epoch 9 - iter 2232/3726 - loss 0.00697985 - time (sec): 279.19 - samples/sec: 440.81 - lr: 0.000001 - momentum: 0.000000
201
+ 2023-10-27 15:44:14,754 epoch 9 - iter 2604/3726 - loss 0.00793074 - time (sec): 325.66 - samples/sec: 440.67 - lr: 0.000001 - momentum: 0.000000
202
+ 2023-10-27 15:45:01,296 epoch 9 - iter 2976/3726 - loss 0.00864270 - time (sec): 372.21 - samples/sec: 439.58 - lr: 0.000001 - momentum: 0.000000
203
+ 2023-10-27 15:45:47,999 epoch 9 - iter 3348/3726 - loss 0.00830012 - time (sec): 418.91 - samples/sec: 438.33 - lr: 0.000001 - momentum: 0.000000
204
+ 2023-10-27 15:46:34,892 epoch 9 - iter 3720/3726 - loss 0.00824128 - time (sec): 465.80 - samples/sec: 438.38 - lr: 0.000001 - momentum: 0.000000
205
+ 2023-10-27 15:46:35,624 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-27 15:46:35,624 EPOCH 9 done: loss 0.0083 - lr: 0.000001
207
+ 2023-10-27 15:46:59,614 DEV : loss 0.05303654819726944 - f1-score (micro avg) 0.9734
208
+ 2023-10-27 15:46:59,675 saving best model
209
+ 2023-10-27 15:47:02,455 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-27 15:47:49,146 epoch 10 - iter 372/3726 - loss 0.00384825 - time (sec): 46.69 - samples/sec: 434.52 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-27 15:48:35,604 epoch 10 - iter 744/3726 - loss 0.00345501 - time (sec): 93.15 - samples/sec: 434.11 - lr: 0.000000 - momentum: 0.000000
212
+ 2023-10-27 15:49:22,080 epoch 10 - iter 1116/3726 - loss 0.00418854 - time (sec): 139.62 - samples/sec: 435.29 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-27 15:50:08,505 epoch 10 - iter 1488/3726 - loss 0.00522497 - time (sec): 186.05 - samples/sec: 430.51 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-27 15:50:54,906 epoch 10 - iter 1860/3726 - loss 0.00509842 - time (sec): 232.45 - samples/sec: 435.12 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-27 15:51:41,148 epoch 10 - iter 2232/3726 - loss 0.00554209 - time (sec): 278.69 - samples/sec: 437.63 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-27 15:52:26,664 epoch 10 - iter 2604/3726 - loss 0.00584885 - time (sec): 324.21 - samples/sec: 441.07 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-27 15:53:13,641 epoch 10 - iter 2976/3726 - loss 0.00599832 - time (sec): 371.18 - samples/sec: 440.13 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-27 15:53:59,425 epoch 10 - iter 3348/3726 - loss 0.00600259 - time (sec): 416.97 - samples/sec: 442.42 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-27 15:54:45,541 epoch 10 - iter 3720/3726 - loss 0.00576228 - time (sec): 463.08 - samples/sec: 441.09 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-27 15:54:46,272 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-27 15:54:46,273 EPOCH 10 done: loss 0.0058 - lr: 0.000000
222
+ 2023-10-27 15:55:09,835 DEV : loss 0.05434899777173996 - f1-score (micro avg) 0.9727
223
+ 2023-10-27 15:55:12,069 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-27 15:55:12,071 Loading model from best epoch ...
225
+ 2023-10-27 15:55:20,258 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 15:55:43,551
227
+ Results:
228
+ - F-score (micro) 0.97
229
+ - F-score (macro) 0.9642
230
+ - Accuracy 0.9559
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ ORG 0.9700 0.9665 0.9682 1909
236
+ PER 0.9944 0.9956 0.9950 1591
237
+ LOC 0.9684 0.9745 0.9714 1413
238
+ MISC 0.9245 0.9200 0.9222 812
239
+
240
+ micro avg 0.9700 0.9700 0.9700 5725
241
+ macro avg 0.9643 0.9641 0.9642 5725
242
+ weighted avg 0.9699 0.9700 0.9699 5725
243
+
244
+ 2023-10-27 15:55:43,551 ----------------------------------------------------------------------------------------------------