Hugging Face's logo

stefan-it
/
hmbench-newseye-sv-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
Swedish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
7e5dc9d
•
1 Parent(s): f38636d

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 21:28:09,101 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:28:09,102 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 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=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-25 21:28:09,102 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:28:09,102 MultiCorpus: 1085 train + 148 dev + 364 test sentences
52
+ - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator
53
+ 2023-10-25 21:28:09,102 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:28:09,103 Train: 1085 sentences
55
+ 2023-10-25 21:28:09,103 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:28:09,103 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:28:09,103 Training Params:
58
+ 2023-10-25 21:28:09,103 - learning_rate: "5e-05"
59
+ 2023-10-25 21:28:09,103 - mini_batch_size: "4"
60
+ 2023-10-25 21:28:09,103 - max_epochs: "10"
61
+ 2023-10-25 21:28:09,103 - shuffle: "True"
62
+ 2023-10-25 21:28:09,103 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:28:09,103 Plugins:
64
+ 2023-10-25 21:28:09,103 - TensorboardLogger
65
+ 2023-10-25 21:28:09,103 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:28:09,103 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:28:09,103 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:28:09,103 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:28:09,103 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:28:09,103 Computation:
71
+ 2023-10-25 21:28:09,103 - compute on device: cuda:0
72
+ 2023-10-25 21:28:09,103 - embedding storage: none
73
+ 2023-10-25 21:28:09,103 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:28:09,103 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-25 21:28:09,103 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:28:09,103 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:28:09,103 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:28:10,568 epoch 1 - iter 27/272 - loss 2.78765850 - time (sec): 1.46 - samples/sec: 3749.30 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-25 21:28:12,027 epoch 1 - iter 54/272 - loss 2.00101582 - time (sec): 2.92 - samples/sec: 3713.94 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-25 21:28:13,451 epoch 1 - iter 81/272 - loss 1.57394260 - time (sec): 4.35 - samples/sec: 3560.78 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-25 21:28:14,978 epoch 1 - iter 108/272 - loss 1.25429045 - time (sec): 5.87 - samples/sec: 3555.28 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-25 21:28:16,446 epoch 1 - iter 135/272 - loss 1.07013551 - time (sec): 7.34 - samples/sec: 3469.41 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-25 21:28:17,961 epoch 1 - iter 162/272 - loss 0.92511254 - time (sec): 8.86 - samples/sec: 3510.43 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-25 21:28:19,538 epoch 1 - iter 189/272 - loss 0.82909206 - time (sec): 10.43 - samples/sec: 3458.10 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-25 21:28:21,053 epoch 1 - iter 216/272 - loss 0.74558155 - time (sec): 11.95 - samples/sec: 3467.28 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-25 21:28:22,540 epoch 1 - iter 243/272 - loss 0.68899771 - time (sec): 13.44 - samples/sec: 3437.71 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-25 21:28:24,103 epoch 1 - iter 270/272 - loss 0.64040727 - time (sec): 15.00 - samples/sec: 3450.74 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-25 21:28:24,209 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:28:24,209 EPOCH 1 done: loss 0.6380 - lr: 0.000049
90
+ 2023-10-25 21:28:24,928 DEV : loss 0.14035949110984802 - f1-score (micro avg) 0.6881
91
+ 2023-10-25 21:28:24,934 saving best model
92
+ 2023-10-25 21:28:25,364 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:28:26,882 epoch 2 - iter 27/272 - loss 0.09840230 - time (sec): 1.52 - samples/sec: 3106.26 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-25 21:28:28,448 epoch 2 - iter 54/272 - loss 0.09235375 - time (sec): 3.08 - samples/sec: 3434.25 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 21:28:30,007 epoch 2 - iter 81/272 - loss 0.11428755 - time (sec): 4.64 - samples/sec: 3233.28 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 21:28:31,513 epoch 2 - iter 108/272 - loss 0.11632033 - time (sec): 6.15 - samples/sec: 3451.06 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 21:28:33,039 epoch 2 - iter 135/272 - loss 0.11619477 - time (sec): 7.67 - samples/sec: 3453.70 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 21:28:34,571 epoch 2 - iter 162/272 - loss 0.11865776 - time (sec): 9.21 - samples/sec: 3407.72 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 21:28:36,059 epoch 2 - iter 189/272 - loss 0.11920523 - time (sec): 10.69 - samples/sec: 3470.34 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 21:28:37,574 epoch 2 - iter 216/272 - loss 0.11666654 - time (sec): 12.21 - samples/sec: 3540.98 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 21:28:39,053 epoch 2 - iter 243/272 - loss 0.11787206 - time (sec): 13.69 - samples/sec: 3477.79 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 21:28:40,560 epoch 2 - iter 270/272 - loss 0.12009223 - time (sec): 15.19 - samples/sec: 3412.65 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-25 21:28:40,657 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:28:40,657 EPOCH 2 done: loss 0.1202 - lr: 0.000045
105
+ 2023-10-25 21:28:41,905 DEV : loss 0.12892909348011017 - f1-score (micro avg) 0.7395
106
+ 2023-10-25 21:28:41,911 saving best model
107
+ 2023-10-25 21:28:42,606 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:28:44,437 epoch 3 - iter 27/272 - loss 0.09342546 - time (sec): 1.82 - samples/sec: 2742.45 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-25 21:28:45,908 epoch 3 - iter 54/272 - loss 0.07117048 - time (sec): 3.29 - samples/sec: 3278.77 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 21:28:47,432 epoch 3 - iter 81/272 - loss 0.06750136 - time (sec): 4.81 - samples/sec: 3238.86 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-25 21:28:48,965 epoch 3 - iter 108/272 - loss 0.06927074 - time (sec): 6.34 - samples/sec: 3317.73 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 21:28:50,533 epoch 3 - iter 135/272 - loss 0.06639235 - time (sec): 7.91 - samples/sec: 3380.15 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-25 21:28:52,011 epoch 3 - iter 162/272 - loss 0.06610577 - time (sec): 9.39 - samples/sec: 3350.69 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 21:28:53,559 epoch 3 - iter 189/272 - loss 0.07007724 - time (sec): 10.94 - samples/sec: 3314.61 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-25 21:28:55,123 epoch 3 - iter 216/272 - loss 0.06922837 - time (sec): 12.50 - samples/sec: 3315.90 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-25 21:28:56,720 epoch 3 - iter 243/272 - loss 0.06963662 - time (sec): 14.10 - samples/sec: 3284.26 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-25 21:28:58,265 epoch 3 - iter 270/272 - loss 0.06919947 - time (sec): 15.64 - samples/sec: 3310.51 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-25 21:28:58,371 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:28:58,371 EPOCH 3 done: loss 0.0690 - lr: 0.000039
120
+ 2023-10-25 21:28:59,614 DEV : loss 0.1450655460357666 - f1-score (micro avg) 0.7698
121
+ 2023-10-25 21:28:59,620 saving best model
122
+ 2023-10-25 21:29:00,271 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:29:01,797 epoch 4 - iter 27/272 - loss 0.03839164 - time (sec): 1.52 - samples/sec: 3389.43 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-25 21:29:03,246 epoch 4 - iter 54/272 - loss 0.05836842 - time (sec): 2.97 - samples/sec: 3375.16 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-25 21:29:04,837 epoch 4 - iter 81/272 - loss 0.05467419 - time (sec): 4.56 - samples/sec: 3543.96 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-25 21:29:06,369 epoch 4 - iter 108/272 - loss 0.05545031 - time (sec): 6.09 - samples/sec: 3456.12 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-25 21:29:07,934 epoch 4 - iter 135/272 - loss 0.05172334 - time (sec): 7.66 - samples/sec: 3437.62 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-25 21:29:09,467 epoch 4 - iter 162/272 - loss 0.05002860 - time (sec): 9.19 - samples/sec: 3467.60 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-25 21:29:10,944 epoch 4 - iter 189/272 - loss 0.04822871 - time (sec): 10.67 - samples/sec: 3465.66 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-25 21:29:12,476 epoch 4 - iter 216/272 - loss 0.04524283 - time (sec): 12.20 - samples/sec: 3457.22 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-25 21:29:13,983 epoch 4 - iter 243/272 - loss 0.04533348 - time (sec): 13.71 - samples/sec: 3443.64 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-25 21:29:15,536 epoch 4 - iter 270/272 - loss 0.04712815 - time (sec): 15.26 - samples/sec: 3395.72 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-25 21:29:15,635 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:29:15,636 EPOCH 4 done: loss 0.0470 - lr: 0.000033
135
+ 2023-10-25 21:29:16,808 DEV : loss 0.14436790347099304 - f1-score (micro avg) 0.7925
136
+ 2023-10-25 21:29:16,814 saving best model
137
+ 2023-10-25 21:29:17,460 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:29:19,028 epoch 5 - iter 27/272 - loss 0.02507648 - time (sec): 1.56 - samples/sec: 3238.49 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-25 21:29:20,566 epoch 5 - iter 54/272 - loss 0.03155307 - time (sec): 3.10 - samples/sec: 3166.66 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-25 21:29:22,132 epoch 5 - iter 81/272 - loss 0.02739434 - time (sec): 4.67 - samples/sec: 3166.84 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-25 21:29:23,726 epoch 5 - iter 108/272 - loss 0.02941651 - time (sec): 6.26 - samples/sec: 3191.64 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-25 21:29:25,199 epoch 5 - iter 135/272 - loss 0.02739614 - time (sec): 7.74 - samples/sec: 3135.22 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-25 21:29:26,698 epoch 5 - iter 162/272 - loss 0.03066702 - time (sec): 9.23 - samples/sec: 3237.55 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-25 21:29:28,219 epoch 5 - iter 189/272 - loss 0.03167286 - time (sec): 10.76 - samples/sec: 3268.30 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-25 21:29:29,737 epoch 5 - iter 216/272 - loss 0.03130840 - time (sec): 12.27 - samples/sec: 3274.44 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-25 21:29:31,274 epoch 5 - iter 243/272 - loss 0.03201179 - time (sec): 13.81 - samples/sec: 3346.11 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-25 21:29:32,794 epoch 5 - iter 270/272 - loss 0.03426102 - time (sec): 15.33 - samples/sec: 3380.00 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-25 21:29:32,902 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:29:32,902 EPOCH 5 done: loss 0.0342 - lr: 0.000028
150
+ 2023-10-25 21:29:34,118 DEV : loss 0.1501101553440094 - f1-score (micro avg) 0.7964
151
+ 2023-10-25 21:29:34,124 saving best model
152
+ 2023-10-25 21:29:34,805 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-25 21:29:36,368 epoch 6 - iter 27/272 - loss 0.01909779 - time (sec): 1.56 - samples/sec: 3493.85 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-25 21:29:37,843 epoch 6 - iter 54/272 - loss 0.01727977 - time (sec): 3.04 - samples/sec: 3533.53 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-25 21:29:39,322 epoch 6 - iter 81/272 - loss 0.01553708 - time (sec): 4.51 - samples/sec: 3427.14 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-25 21:29:40,841 epoch 6 - iter 108/272 - loss 0.01998247 - time (sec): 6.03 - samples/sec: 3439.13 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-25 21:29:42,736 epoch 6 - iter 135/272 - loss 0.01744104 - time (sec): 7.93 - samples/sec: 3234.22 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-25 21:29:44,174 epoch 6 - iter 162/272 - loss 0.01847424 - time (sec): 9.37 - samples/sec: 3320.47 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-25 21:29:45,642 epoch 6 - iter 189/272 - loss 0.01935988 - time (sec): 10.83 - samples/sec: 3383.82 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-25 21:29:47,102 epoch 6 - iter 216/272 - loss 0.01931684 - time (sec): 12.29 - samples/sec: 3326.04 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-25 21:29:48,602 epoch 6 - iter 243/272 - loss 0.01934257 - time (sec): 13.79 - samples/sec: 3372.67 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-25 21:29:50,066 epoch 6 - iter 270/272 - loss 0.02070140 - time (sec): 15.26 - samples/sec: 3379.89 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-25 21:29:50,171 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-25 21:29:50,172 EPOCH 6 done: loss 0.0205 - lr: 0.000022
165
+ 2023-10-25 21:29:51,433 DEV : loss 0.165546253323555 - f1-score (micro avg) 0.8066
166
+ 2023-10-25 21:29:51,440 saving best model
167
+ 2023-10-25 21:29:54,714 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-25 21:29:56,247 epoch 7 - iter 27/272 - loss 0.00697830 - time (sec): 1.53 - samples/sec: 3623.25 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-25 21:29:57,777 epoch 7 - iter 54/272 - loss 0.00914022 - time (sec): 3.06 - samples/sec: 3451.66 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-25 21:29:59,278 epoch 7 - iter 81/272 - loss 0.00936467 - time (sec): 4.56 - samples/sec: 3464.62 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-25 21:30:00,780 epoch 7 - iter 108/272 - loss 0.00900487 - time (sec): 6.06 - samples/sec: 3543.39 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-25 21:30:02,352 epoch 7 - iter 135/272 - loss 0.01188333 - time (sec): 7.64 - samples/sec: 3443.14 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-25 21:30:03,855 epoch 7 - iter 162/272 - loss 0.01348404 - time (sec): 9.14 - samples/sec: 3432.95 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-25 21:30:05,413 epoch 7 - iter 189/272 - loss 0.01577447 - time (sec): 10.70 - samples/sec: 3464.67 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-25 21:30:06,948 epoch 7 - iter 216/272 - loss 0.01509764 - time (sec): 12.23 - samples/sec: 3455.51 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-25 21:30:08,406 epoch 7 - iter 243/272 - loss 0.01702924 - time (sec): 13.69 - samples/sec: 3423.92 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-25 21:30:09,929 epoch 7 - iter 270/272 - loss 0.01657090 - time (sec): 15.21 - samples/sec: 3393.89 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-25 21:30:10,042 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-25 21:30:10,042 EPOCH 7 done: loss 0.0165 - lr: 0.000017
180
+ 2023-10-25 21:30:11,380 DEV : loss 0.18749994039535522 - f1-score (micro avg) 0.8036
181
+ 2023-10-25 21:30:11,386 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-25 21:30:12,890 epoch 8 - iter 27/272 - loss 0.01739788 - time (sec): 1.50 - samples/sec: 4044.12 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-25 21:30:14,357 epoch 8 - iter 54/272 - loss 0.01871958 - time (sec): 2.97 - samples/sec: 3716.48 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-25 21:30:15,894 epoch 8 - iter 81/272 - loss 0.01462857 - time (sec): 4.51 - samples/sec: 3692.83 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-25 21:30:17,387 epoch 8 - iter 108/272 - loss 0.01387024 - time (sec): 6.00 - samples/sec: 3631.22 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-25 21:30:18,930 epoch 8 - iter 135/272 - loss 0.01409383 - time (sec): 7.54 - samples/sec: 3613.71 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-25 21:30:20,417 epoch 8 - iter 162/272 - loss 0.01425509 - time (sec): 9.03 - samples/sec: 3556.26 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-25 21:30:21,950 epoch 8 - iter 189/272 - loss 0.01373470 - time (sec): 10.56 - samples/sec: 3529.86 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-25 21:30:23,498 epoch 8 - iter 216/272 - loss 0.01224350 - time (sec): 12.11 - samples/sec: 3512.96 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-25 21:30:25,052 epoch 8 - iter 243/272 - loss 0.01131915 - time (sec): 13.67 - samples/sec: 3470.03 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-25 21:30:26,502 epoch 8 - iter 270/272 - loss 0.01157460 - time (sec): 15.12 - samples/sec: 3431.48 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-25 21:30:26,605 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-25 21:30:26,605 EPOCH 8 done: loss 0.0115 - lr: 0.000011
194
+ 2023-10-25 21:30:27,835 DEV : loss 0.17698289453983307 - f1-score (micro avg) 0.8266
195
+ 2023-10-25 21:30:27,841 saving best model
196
+ 2023-10-25 21:30:28,465 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-25 21:30:30,036 epoch 9 - iter 27/272 - loss 0.00058588 - time (sec): 1.57 - samples/sec: 3749.18 - lr: 0.000011 - momentum: 0.000000
198
+ 2023-10-25 21:30:31,531 epoch 9 - iter 54/272 - loss 0.00623629 - time (sec): 3.06 - samples/sec: 3569.82 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-25 21:30:33,037 epoch 9 - iter 81/272 - loss 0.00539403 - time (sec): 4.57 - samples/sec: 3400.69 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-25 21:30:34,548 epoch 9 - iter 108/272 - loss 0.00741251 - time (sec): 6.08 - samples/sec: 3341.22 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-25 21:30:36,038 epoch 9 - iter 135/272 - loss 0.00926729 - time (sec): 7.57 - samples/sec: 3391.09 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-25 21:30:37,554 epoch 9 - iter 162/272 - loss 0.00852067 - time (sec): 9.09 - samples/sec: 3414.77 - lr: 0.000008 - momentum: 0.000000
203
+ 2023-10-25 21:30:39,074 epoch 9 - iter 189/272 - loss 0.00788998 - time (sec): 10.61 - samples/sec: 3466.92 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-25 21:30:40,588 epoch 9 - iter 216/272 - loss 0.00711701 - time (sec): 12.12 - samples/sec: 3418.25 - lr: 0.000007 - momentum: 0.000000
205
+ 2023-10-25 21:30:42,061 epoch 9 - iter 243/272 - loss 0.00659543 - time (sec): 13.59 - samples/sec: 3439.13 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-25 21:30:43,592 epoch 9 - iter 270/272 - loss 0.00744715 - time (sec): 15.13 - samples/sec: 3427.52 - lr: 0.000006 - momentum: 0.000000
207
+ 2023-10-25 21:30:43,695 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-25 21:30:43,696 EPOCH 9 done: loss 0.0074 - lr: 0.000006
209
+ 2023-10-25 21:30:45,471 DEV : loss 0.1907862275838852 - f1-score (micro avg) 0.822
210
+ 2023-10-25 21:30:45,478 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-25 21:30:46,944 epoch 10 - iter 27/272 - loss 0.00585267 - time (sec): 1.47 - samples/sec: 3723.63 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-25 21:30:48,393 epoch 10 - iter 54/272 - loss 0.00495959 - time (sec): 2.91 - samples/sec: 3508.61 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-25 21:30:49,885 epoch 10 - iter 81/272 - loss 0.00450007 - time (sec): 4.41 - samples/sec: 3559.91 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-25 21:30:51,343 epoch 10 - iter 108/272 - loss 0.00425761 - time (sec): 5.86 - samples/sec: 3633.67 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-25 21:30:52,829 epoch 10 - iter 135/272 - loss 0.00470265 - time (sec): 7.35 - samples/sec: 3550.95 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-25 21:30:54,275 epoch 10 - iter 162/272 - loss 0.00419178 - time (sec): 8.80 - samples/sec: 3540.66 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-25 21:30:55,718 epoch 10 - iter 189/272 - loss 0.00450719 - time (sec): 10.24 - samples/sec: 3586.16 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-25 21:30:57,167 epoch 10 - iter 216/272 - loss 0.00419873 - time (sec): 11.69 - samples/sec: 3564.16 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-25 21:30:58,628 epoch 10 - iter 243/272 - loss 0.00473732 - time (sec): 13.15 - samples/sec: 3537.51 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-25 21:31:00,035 epoch 10 - iter 270/272 - loss 0.00519675 - time (sec): 14.56 - samples/sec: 3555.18 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-25 21:31:00,128 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-25 21:31:00,128 EPOCH 10 done: loss 0.0052 - lr: 0.000000
223
+ 2023-10-25 21:31:01,313 DEV : loss 0.19103476405143738 - f1-score (micro avg) 0.8205
224
+ 2023-10-25 21:31:01,785 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-25 21:31:01,786 Loading model from best epoch ...
226
+ 2023-10-25 21:31:03,678 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG
227
+ 2023-10-25 21:31:05,500
228
+ Results:
229
+ - F-score (micro) 0.7823
230
+ - F-score (macro) 0.7373
231
+ - Accuracy 0.664
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.8000 0.8718 0.8344 312
237
+ PER 0.6947 0.8750 0.7745 208
238
+ ORG 0.4545 0.3636 0.4040 55
239
+ HumanProd 0.8800 1.0000 0.9362 22
240
+
241
+ micro avg 0.7392 0.8308 0.7823 597
242
+ macro avg 0.7073 0.7776 0.7373 597
243
+ weighted avg 0.7344 0.8308 0.7776 597
244
+
245
+ 2023-10-25 21:31:05,500 ----------------------------------------------------------------------------------------------------