Hugging Face's logo

stefan-it
/
hmbench-newseye-de-hmbert-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
2
stefan-it commited on
Commit
c9e3987
•
1 Parent(s): 2b69d76

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 +238 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf4f8fd627e625972316e9145e9cb9dcca9490f2fc826271add2264432615be
3
+ size 443323527
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 14:04:50 0.0000 0.4501 0.1400 0.1972 0.5095 0.2844 0.1666
3
+ 2 14:08:08 0.0000 0.1462 0.1336 0.3029 0.5473 0.3900 0.2435
4
+ 3 14:11:27 0.0000 0.0983 0.3090 0.2249 0.6970 0.3401 0.2052
5
+ 4 14:14:45 0.0000 0.0681 0.2435 0.2895 0.5000 0.3667 0.2253
6
+ 5 14:18:03 0.0000 0.0505 0.3341 0.2760 0.6136 0.3807 0.2368
7
+ 6 14:21:20 0.0000 0.0367 0.3697 0.2731 0.5777 0.3708 0.2286
8
+ 7 14:24:36 0.0000 0.0274 0.4079 0.2690 0.6023 0.3719 0.2296
9
+ 8 14:27:54 0.0000 0.0193 0.4761 0.2734 0.6042 0.3764 0.2330
10
+ 9 14:31:11 0.0000 0.0144 0.5071 0.2508 0.6193 0.3570 0.2184
11
+ 10 14:34:28 0.0000 0.0099 0.5089 0.2648 0.6420 0.3750 0.2319
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-15 14:01:36,257 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-15 14:01:36,258 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=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-15 14:01:36,258 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-15 14:01:36,258 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences
52
+ - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator
53
+ 2023-10-15 14:01:36,258 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-15 14:01:36,258 Train: 20847 sentences
55
+ 2023-10-15 14:01:36,258 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-15 14:01:36,258 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-15 14:01:36,258 Training Params:
58
+ 2023-10-15 14:01:36,258 - learning_rate: "3e-05"
59
+ 2023-10-15 14:01:36,258 - mini_batch_size: "8"
60
+ 2023-10-15 14:01:36,258 - max_epochs: "10"
61
+ 2023-10-15 14:01:36,259 - shuffle: "True"
62
+ 2023-10-15 14:01:36,259 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-15 14:01:36,259 Plugins:
64
+ 2023-10-15 14:01:36,259 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-15 14:01:36,259 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-15 14:01:36,259 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-15 14:01:36,259 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-15 14:01:36,259 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-15 14:01:36,259 Computation:
70
+ 2023-10-15 14:01:36,259 - compute on device: cuda:0
71
+ 2023-10-15 14:01:36,259 - embedding storage: none
72
+ 2023-10-15 14:01:36,259 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-15 14:01:36,259 Model training base path: "hmbench-newseye/de-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
74
+ 2023-10-15 14:01:36,259 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-15 14:01:36,259 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-15 14:01:55,792 epoch 1 - iter 260/2606 - loss 2.10500958 - time (sec): 19.53 - samples/sec: 1932.41 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-15 14:02:15,076 epoch 1 - iter 520/2606 - loss 1.26983835 - time (sec): 38.82 - samples/sec: 1922.46 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-15 14:02:34,769 epoch 1 - iter 780/2606 - loss 0.94395616 - time (sec): 58.51 - samples/sec: 1956.46 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-15 14:02:53,143 epoch 1 - iter 1040/2606 - loss 0.79513165 - time (sec): 76.88 - samples/sec: 1943.46 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-15 14:03:11,642 epoch 1 - iter 1300/2606 - loss 0.68606228 - time (sec): 95.38 - samples/sec: 1952.23 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-15 14:03:30,437 epoch 1 - iter 1560/2606 - loss 0.61116996 - time (sec): 114.18 - samples/sec: 1953.28 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-15 14:03:49,261 epoch 1 - iter 1820/2606 - loss 0.55490958 - time (sec): 133.00 - samples/sec: 1945.68 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-15 14:04:06,976 epoch 1 - iter 2080/2606 - loss 0.51740975 - time (sec): 150.72 - samples/sec: 1945.69 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-15 14:04:25,979 epoch 1 - iter 2340/2606 - loss 0.47955013 - time (sec): 169.72 - samples/sec: 1946.46 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-15 14:04:44,448 epoch 1 - iter 2600/2606 - loss 0.45046229 - time (sec): 188.19 - samples/sec: 1946.99 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-15 14:04:44,960 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-15 14:04:44,960 EPOCH 1 done: loss 0.4501 - lr: 0.000030
88
+ 2023-10-15 14:04:50,762 DEV : loss 0.14003677666187286 - f1-score (micro avg) 0.2844
89
+ 2023-10-15 14:04:50,788 saving best model
90
+ 2023-10-15 14:04:51,134 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-15 14:05:09,702 epoch 2 - iter 260/2606 - loss 0.15343561 - time (sec): 18.57 - samples/sec: 1884.69 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-15 14:05:28,205 epoch 2 - iter 520/2606 - loss 0.15178841 - time (sec): 37.07 - samples/sec: 1922.84 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-15 14:05:47,186 epoch 2 - iter 780/2606 - loss 0.16502854 - time (sec): 56.05 - samples/sec: 1943.13 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-15 14:06:05,881 epoch 2 - iter 1040/2606 - loss 0.15965107 - time (sec): 74.75 - samples/sec: 1937.79 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-15 14:06:24,879 epoch 2 - iter 1300/2606 - loss 0.15210531 - time (sec): 93.74 - samples/sec: 1938.76 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-15 14:06:44,999 epoch 2 - iter 1560/2606 - loss 0.15153758 - time (sec): 113.86 - samples/sec: 1931.12 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-15 14:07:03,975 epoch 2 - iter 1820/2606 - loss 0.15458329 - time (sec): 132.84 - samples/sec: 1927.42 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-15 14:07:22,929 epoch 2 - iter 2080/2606 - loss 0.15036258 - time (sec): 151.79 - samples/sec: 1939.42 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-15 14:07:41,239 epoch 2 - iter 2340/2606 - loss 0.14805015 - time (sec): 170.10 - samples/sec: 1941.09 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-15 14:07:59,299 epoch 2 - iter 2600/2606 - loss 0.14621051 - time (sec): 188.16 - samples/sec: 1947.42 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-15 14:07:59,743 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-15 14:07:59,743 EPOCH 2 done: loss 0.1462 - lr: 0.000027
103
+ 2023-10-15 14:08:08,774 DEV : loss 0.13364139199256897 - f1-score (micro avg) 0.39
104
+ 2023-10-15 14:08:08,801 saving best model
105
+ 2023-10-15 14:08:09,245 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-15 14:08:28,868 epoch 3 - iter 260/2606 - loss 0.09480531 - time (sec): 19.62 - samples/sec: 1974.43 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-15 14:08:48,315 epoch 3 - iter 520/2606 - loss 0.09762294 - time (sec): 39.07 - samples/sec: 1983.56 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-15 14:09:07,080 epoch 3 - iter 780/2606 - loss 0.09675264 - time (sec): 57.83 - samples/sec: 1980.67 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-15 14:09:25,697 epoch 3 - iter 1040/2606 - loss 0.09948955 - time (sec): 76.45 - samples/sec: 1965.21 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-15 14:09:45,450 epoch 3 - iter 1300/2606 - loss 0.09948710 - time (sec): 96.20 - samples/sec: 1957.06 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-15 14:10:03,728 epoch 3 - iter 1560/2606 - loss 0.09994118 - time (sec): 114.48 - samples/sec: 1944.58 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-15 14:10:22,050 epoch 3 - iter 1820/2606 - loss 0.10105418 - time (sec): 132.80 - samples/sec: 1940.74 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-15 14:10:40,160 epoch 3 - iter 2080/2606 - loss 0.10069437 - time (sec): 150.91 - samples/sec: 1941.19 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-15 14:10:59,724 epoch 3 - iter 2340/2606 - loss 0.09900983 - time (sec): 170.48 - samples/sec: 1937.15 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-15 14:11:18,082 epoch 3 - iter 2600/2606 - loss 0.09855936 - time (sec): 188.83 - samples/sec: 1937.91 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-15 14:11:18,766 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-15 14:11:18,767 EPOCH 3 done: loss 0.0983 - lr: 0.000023
118
+ 2023-10-15 14:11:27,767 DEV : loss 0.3090475797653198 - f1-score (micro avg) 0.3401
119
+ 2023-10-15 14:11:27,807 ----------------------------------------------------------------------------------------------------
120
+ 2023-10-15 14:11:47,935 epoch 4 - iter 260/2606 - loss 0.06471452 - time (sec): 20.13 - samples/sec: 1920.58 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-15 14:12:05,741 epoch 4 - iter 520/2606 - loss 0.06762329 - time (sec): 37.93 - samples/sec: 1906.81 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-15 14:12:24,546 epoch 4 - iter 780/2606 - loss 0.06800522 - time (sec): 56.74 - samples/sec: 1930.44 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-15 14:12:42,675 epoch 4 - iter 1040/2606 - loss 0.06657946 - time (sec): 74.87 - samples/sec: 1938.41 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-15 14:13:01,137 epoch 4 - iter 1300/2606 - loss 0.06471875 - time (sec): 93.33 - samples/sec: 1948.71 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-15 14:13:20,193 epoch 4 - iter 1560/2606 - loss 0.06505784 - time (sec): 112.38 - samples/sec: 1951.95 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-15 14:13:38,849 epoch 4 - iter 1820/2606 - loss 0.06630090 - time (sec): 131.04 - samples/sec: 1949.47 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-15 14:13:57,364 epoch 4 - iter 2080/2606 - loss 0.06697785 - time (sec): 149.56 - samples/sec: 1944.52 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-15 14:14:17,007 epoch 4 - iter 2340/2606 - loss 0.06760635 - time (sec): 169.20 - samples/sec: 1944.05 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-15 14:14:36,161 epoch 4 - iter 2600/2606 - loss 0.06815817 - time (sec): 188.35 - samples/sec: 1946.62 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-15 14:14:36,569 ----------------------------------------------------------------------------------------------------
131
+ 2023-10-15 14:14:36,570 EPOCH 4 done: loss 0.0681 - lr: 0.000020
132
+ 2023-10-15 14:14:45,494 DEV : loss 0.24350780248641968 - f1-score (micro avg) 0.3667
133
+ 2023-10-15 14:14:45,521 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-15 14:15:03,951 epoch 5 - iter 260/2606 - loss 0.04722609 - time (sec): 18.43 - samples/sec: 1993.69 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-15 14:15:24,644 epoch 5 - iter 520/2606 - loss 0.04908254 - time (sec): 39.12 - samples/sec: 1995.90 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-15 14:15:43,022 epoch 5 - iter 780/2606 - loss 0.04697712 - time (sec): 57.50 - samples/sec: 1977.43 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-15 14:16:02,706 epoch 5 - iter 1040/2606 - loss 0.04721646 - time (sec): 77.18 - samples/sec: 1973.46 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-15 14:16:20,741 epoch 5 - iter 1300/2606 - loss 0.04714736 - time (sec): 95.22 - samples/sec: 1971.98 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-15 14:16:40,230 epoch 5 - iter 1560/2606 - loss 0.04707598 - time (sec): 114.71 - samples/sec: 1967.68 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-15 14:16:59,025 epoch 5 - iter 1820/2606 - loss 0.04670234 - time (sec): 133.50 - samples/sec: 1951.10 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-15 14:17:17,213 epoch 5 - iter 2080/2606 - loss 0.04877738 - time (sec): 151.69 - samples/sec: 1949.95 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-15 14:17:36,115 epoch 5 - iter 2340/2606 - loss 0.05008815 - time (sec): 170.59 - samples/sec: 1954.53 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-15 14:17:53,766 epoch 5 - iter 2600/2606 - loss 0.05049142 - time (sec): 188.24 - samples/sec: 1948.52 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-15 14:17:54,153 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-15 14:17:54,153 EPOCH 5 done: loss 0.0505 - lr: 0.000017
146
+ 2023-10-15 14:18:03,078 DEV : loss 0.33405596017837524 - f1-score (micro avg) 0.3807
147
+ 2023-10-15 14:18:03,104 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-15 14:18:22,812 epoch 6 - iter 260/2606 - loss 0.02891067 - time (sec): 19.71 - samples/sec: 1956.11 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-15 14:18:40,995 epoch 6 - iter 520/2606 - loss 0.03662193 - time (sec): 37.89 - samples/sec: 1964.56 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-15 14:18:59,480 epoch 6 - iter 780/2606 - loss 0.03599884 - time (sec): 56.37 - samples/sec: 1978.28 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-15 14:19:17,797 epoch 6 - iter 1040/2606 - loss 0.03753291 - time (sec): 74.69 - samples/sec: 1951.04 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-15 14:19:37,287 epoch 6 - iter 1300/2606 - loss 0.03732199 - time (sec): 94.18 - samples/sec: 1952.12 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-15 14:19:56,296 epoch 6 - iter 1560/2606 - loss 0.03809148 - time (sec): 113.19 - samples/sec: 1955.68 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-15 14:20:16,435 epoch 6 - iter 1820/2606 - loss 0.03657832 - time (sec): 133.33 - samples/sec: 1960.96 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-15 14:20:34,252 epoch 6 - iter 2080/2606 - loss 0.03754956 - time (sec): 151.15 - samples/sec: 1955.27 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-15 14:20:52,808 epoch 6 - iter 2340/2606 - loss 0.03695265 - time (sec): 169.70 - samples/sec: 1952.85 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-15 14:21:11,112 epoch 6 - iter 2600/2606 - loss 0.03678499 - time (sec): 188.01 - samples/sec: 1949.06 - lr: 0.000013 - momentum: 0.000000
158
+ 2023-10-15 14:21:11,590 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-15 14:21:11,591 EPOCH 6 done: loss 0.0367 - lr: 0.000013
160
+ 2023-10-15 14:21:20,530 DEV : loss 0.3696856200695038 - f1-score (micro avg) 0.3708
161
+ 2023-10-15 14:21:20,557 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-15 14:21:38,363 epoch 7 - iter 260/2606 - loss 0.02251214 - time (sec): 17.81 - samples/sec: 1894.53 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-15 14:21:56,785 epoch 7 - iter 520/2606 - loss 0.02776332 - time (sec): 36.23 - samples/sec: 1912.76 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-15 14:22:16,268 epoch 7 - iter 780/2606 - loss 0.02781888 - time (sec): 55.71 - samples/sec: 1940.00 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-15 14:22:34,320 epoch 7 - iter 1040/2606 - loss 0.02918939 - time (sec): 73.76 - samples/sec: 1932.80 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-15 14:22:52,187 epoch 7 - iter 1300/2606 - loss 0.02885109 - time (sec): 91.63 - samples/sec: 1929.34 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-15 14:23:10,587 epoch 7 - iter 1560/2606 - loss 0.02859748 - time (sec): 110.03 - samples/sec: 1942.85 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-15 14:23:29,589 epoch 7 - iter 1820/2606 - loss 0.02842582 - time (sec): 129.03 - samples/sec: 1943.10 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-15 14:23:48,843 epoch 7 - iter 2080/2606 - loss 0.02738935 - time (sec): 148.29 - samples/sec: 1953.11 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-15 14:24:08,024 epoch 7 - iter 2340/2606 - loss 0.02673557 - time (sec): 167.47 - samples/sec: 1961.27 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-15 14:24:27,295 epoch 7 - iter 2600/2606 - loss 0.02752743 - time (sec): 186.74 - samples/sec: 1959.26 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-15 14:24:28,085 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-15 14:24:28,086 EPOCH 7 done: loss 0.0274 - lr: 0.000010
174
+ 2023-10-15 14:24:36,409 DEV : loss 0.40790677070617676 - f1-score (micro avg) 0.3719
175
+ 2023-10-15 14:24:36,438 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-15 14:24:55,407 epoch 8 - iter 260/2606 - loss 0.01291656 - time (sec): 18.97 - samples/sec: 2010.97 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-15 14:25:15,266 epoch 8 - iter 520/2606 - loss 0.01561056 - time (sec): 38.83 - samples/sec: 1931.01 - lr: 0.000009 - momentum: 0.000000
178
+ 2023-10-15 14:25:33,534 epoch 8 - iter 780/2606 - loss 0.01711152 - time (sec): 57.10 - samples/sec: 1900.24 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-15 14:25:52,324 epoch 8 - iter 1040/2606 - loss 0.01692317 - time (sec): 75.88 - samples/sec: 1910.09 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-15 14:26:10,343 epoch 8 - iter 1300/2606 - loss 0.01745508 - time (sec): 93.90 - samples/sec: 1904.76 - lr: 0.000008 - momentum: 0.000000
181
+ 2023-10-15 14:26:29,544 epoch 8 - iter 1560/2606 - loss 0.01789181 - time (sec): 113.11 - samples/sec: 1905.43 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-15 14:26:48,970 epoch 8 - iter 1820/2606 - loss 0.01759359 - time (sec): 132.53 - samples/sec: 1929.92 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-15 14:27:08,447 epoch 8 - iter 2080/2606 - loss 0.01988694 - time (sec): 152.01 - samples/sec: 1934.62 - lr: 0.000007 - momentum: 0.000000
184
+ 2023-10-15 14:27:26,703 epoch 8 - iter 2340/2606 - loss 0.01975246 - time (sec): 170.26 - samples/sec: 1935.81 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-15 14:27:45,522 epoch 8 - iter 2600/2606 - loss 0.01936912 - time (sec): 189.08 - samples/sec: 1938.14 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-15 14:27:45,948 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-15 14:27:45,948 EPOCH 8 done: loss 0.0193 - lr: 0.000007
188
+ 2023-10-15 14:27:54,258 DEV : loss 0.47605660557746887 - f1-score (micro avg) 0.3764
189
+ 2023-10-15 14:27:54,286 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-15 14:28:12,090 epoch 9 - iter 260/2606 - loss 0.01344739 - time (sec): 17.80 - samples/sec: 1944.75 - lr: 0.000006 - momentum: 0.000000
191
+ 2023-10-15 14:28:30,090 epoch 9 - iter 520/2606 - loss 0.01392440 - time (sec): 35.80 - samples/sec: 1912.57 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-15 14:28:49,788 epoch 9 - iter 780/2606 - loss 0.01322424 - time (sec): 55.50 - samples/sec: 1949.28 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-15 14:29:08,912 epoch 9 - iter 1040/2606 - loss 0.01368991 - time (sec): 74.62 - samples/sec: 1945.75 - lr: 0.000005 - momentum: 0.000000
194
+ 2023-10-15 14:29:29,116 epoch 9 - iter 1300/2606 - loss 0.01353773 - time (sec): 94.83 - samples/sec: 1930.19 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-15 14:29:48,188 epoch 9 - iter 1560/2606 - loss 0.01447917 - time (sec): 113.90 - samples/sec: 1929.00 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-15 14:30:07,028 epoch 9 - iter 1820/2606 - loss 0.01464400 - time (sec): 132.74 - samples/sec: 1938.67 - lr: 0.000004 - momentum: 0.000000
197
+ 2023-10-15 14:30:25,120 epoch 9 - iter 2080/2606 - loss 0.01479487 - time (sec): 150.83 - samples/sec: 1947.30 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-15 14:30:43,960 epoch 9 - iter 2340/2606 - loss 0.01446972 - time (sec): 169.67 - samples/sec: 1948.17 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-15 14:31:02,704 epoch 9 - iter 2600/2606 - loss 0.01440697 - time (sec): 188.42 - samples/sec: 1948.19 - lr: 0.000003 - momentum: 0.000000
200
+ 2023-10-15 14:31:02,988 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-15 14:31:02,988 EPOCH 9 done: loss 0.0144 - lr: 0.000003
202
+ 2023-10-15 14:31:11,206 DEV : loss 0.5070585012435913 - f1-score (micro avg) 0.357
203
+ 2023-10-15 14:31:11,233 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-15 14:31:29,933 epoch 10 - iter 260/2606 - loss 0.00817533 - time (sec): 18.70 - samples/sec: 1976.58 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-15 14:31:48,831 epoch 10 - iter 520/2606 - loss 0.01083697 - time (sec): 37.60 - samples/sec: 1963.51 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-15 14:32:08,276 epoch 10 - iter 780/2606 - loss 0.01055400 - time (sec): 57.04 - samples/sec: 1983.88 - lr: 0.000002 - momentum: 0.000000
207
+ 2023-10-15 14:32:26,967 epoch 10 - iter 1040/2606 - loss 0.00978576 - time (sec): 75.73 - samples/sec: 1979.43 - lr: 0.000002 - momentum: 0.000000
208
+ 2023-10-15 14:32:44,756 epoch 10 - iter 1300/2606 - loss 0.00974007 - time (sec): 93.52 - samples/sec: 1969.25 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-15 14:33:03,283 epoch 10 - iter 1560/2606 - loss 0.01014539 - time (sec): 112.05 - samples/sec: 1964.43 - lr: 0.000001 - momentum: 0.000000
210
+ 2023-10-15 14:33:23,915 epoch 10 - iter 1820/2606 - loss 0.01022403 - time (sec): 132.68 - samples/sec: 1946.26 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-15 14:33:42,085 epoch 10 - iter 2080/2606 - loss 0.00970005 - time (sec): 150.85 - samples/sec: 1945.45 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-15 14:34:00,746 epoch 10 - iter 2340/2606 - loss 0.00966883 - time (sec): 169.51 - samples/sec: 1948.61 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-15 14:34:19,225 epoch 10 - iter 2600/2606 - loss 0.00993739 - time (sec): 187.99 - samples/sec: 1947.96 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-15 14:34:19,749 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-15 14:34:19,749 EPOCH 10 done: loss 0.0099 - lr: 0.000000
216
+ 2023-10-15 14:34:28,121 DEV : loss 0.5089101195335388 - f1-score (micro avg) 0.375
217
+ 2023-10-15 14:34:28,509 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-15 14:34:28,510 Loading model from best epoch ...
219
+ 2023-10-15 14:34:30,123 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
220
+ 2023-10-15 14:34:45,633
221
+ Results:
222
+ - F-score (micro) 0.4364
223
+ - F-score (macro) 0.2809
224
+ - Accuracy 0.2836
225
+
226
+ By class:
227
+ precision recall f1-score support
228
+
229
+ LOC 0.5629 0.5198 0.5405 1214
230
+ PER 0.3648 0.4307 0.3950 808
231
+ ORG 0.2026 0.1756 0.1882 353
232
+ HumanProd 0.0000 0.0000 0.0000 15
233
+
234
+ micro avg 0.4372 0.4356 0.4364 2390
235
+ macro avg 0.2826 0.2815 0.2809 2390
236
+ weighted avg 0.4392 0.4356 0.4359 2390
237
+
238
+ 2023-10-15 14:34:45,634 ----------------------------------------------------------------------------------------------------