Upload folder using huggingface_hub
Browse files- best-model.pt +3 -0
- dev.tsv +0 -0
- loss.tsv +11 -0
- runs/events.out.tfevents.1697793508.46dc0c540dd0.5704.3 +3 -0
- test.tsv +0 -0
- training.log +245 -0
best-model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9627ce2787a97155cd0110b4945f7c9a55ecfda59f920cd0cbd0ae0672920d95
|
3 |
+
size 19045986
|
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 09:18:47 0.0000 0.9579 0.1307 0.0000 0.0000 0.0000 0.0000
|
3 |
+
2 09:19:06 0.0000 0.1796 0.0881 0.6345 0.3882 0.4817 0.3297
|
4 |
+
3 09:19:24 0.0000 0.1467 0.0795 0.6324 0.5443 0.5850 0.4329
|
5 |
+
4 09:19:43 0.0000 0.1299 0.0781 0.6862 0.5443 0.6071 0.4607
|
6 |
+
5 09:20:02 0.0000 0.1169 0.0753 0.6439 0.5570 0.5973 0.4536
|
7 |
+
6 09:20:20 0.0000 0.1098 0.0746 0.6351 0.5949 0.6144 0.4747
|
8 |
+
7 09:20:39 0.0000 0.1037 0.0766 0.6282 0.6203 0.6242 0.4836
|
9 |
+
8 09:20:57 0.0000 0.0973 0.0794 0.6574 0.5992 0.6269 0.4863
|
10 |
+
9 09:21:15 0.0000 0.0943 0.0802 0.6774 0.6203 0.6476 0.5034
|
11 |
+
10 09:21:34 0.0000 0.0933 0.0814 0.6758 0.6245 0.6491 0.5051
|
runs/events.out.tfevents.1697793508.46dc0c540dd0.5704.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c674d53abb83609d6cb56982ae40f1db6d09176d83b9c0b0729a7234acb5600
|
3 |
+
size 434848
|
test.tsv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training.log
ADDED
@@ -0,0 +1,245 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2023-10-20 09:18:28,284 ----------------------------------------------------------------------------------------------------
|
2 |
+
2023-10-20 09:18:28,285 Model: "SequenceTagger(
|
3 |
+
(embeddings): TransformerWordEmbeddings(
|
4 |
+
(model): BertModel(
|
5 |
+
(embeddings): BertEmbeddings(
|
6 |
+
(word_embeddings): Embedding(32001, 128)
|
7 |
+
(position_embeddings): Embedding(512, 128)
|
8 |
+
(token_type_embeddings): Embedding(2, 128)
|
9 |
+
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
|
10 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
11 |
+
)
|
12 |
+
(encoder): BertEncoder(
|
13 |
+
(layer): ModuleList(
|
14 |
+
(0-1): 2 x BertLayer(
|
15 |
+
(attention): BertAttention(
|
16 |
+
(self): BertSelfAttention(
|
17 |
+
(query): Linear(in_features=128, out_features=128, bias=True)
|
18 |
+
(key): Linear(in_features=128, out_features=128, bias=True)
|
19 |
+
(value): Linear(in_features=128, out_features=128, bias=True)
|
20 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
21 |
+
)
|
22 |
+
(output): BertSelfOutput(
|
23 |
+
(dense): Linear(in_features=128, out_features=128, bias=True)
|
24 |
+
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
|
25 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
26 |
+
)
|
27 |
+
)
|
28 |
+
(intermediate): BertIntermediate(
|
29 |
+
(dense): Linear(in_features=128, out_features=512, bias=True)
|
30 |
+
(intermediate_act_fn): GELUActivation()
|
31 |
+
)
|
32 |
+
(output): BertOutput(
|
33 |
+
(dense): Linear(in_features=512, out_features=128, bias=True)
|
34 |
+
(LayerNorm): LayerNorm((128,), 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=128, out_features=128, bias=True)
|
42 |
+
(activation): Tanh()
|
43 |
+
)
|
44 |
+
)
|
45 |
+
)
|
46 |
+
(locked_dropout): LockedDropout(p=0.5)
|
47 |
+
(linear): Linear(in_features=128, out_features=13, bias=True)
|
48 |
+
(loss_function): CrossEntropyLoss()
|
49 |
+
)"
|
50 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
51 |
+
2023-10-20 09:18:28,285 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
|
52 |
+
- NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
|
53 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
54 |
+
2023-10-20 09:18:28,285 Train: 6183 sentences
|
55 |
+
2023-10-20 09:18:28,285 (train_with_dev=False, train_with_test=False)
|
56 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
57 |
+
2023-10-20 09:18:28,285 Training Params:
|
58 |
+
2023-10-20 09:18:28,285 - learning_rate: "5e-05"
|
59 |
+
2023-10-20 09:18:28,285 - mini_batch_size: "8"
|
60 |
+
2023-10-20 09:18:28,285 - max_epochs: "10"
|
61 |
+
2023-10-20 09:18:28,285 - shuffle: "True"
|
62 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
63 |
+
2023-10-20 09:18:28,285 Plugins:
|
64 |
+
2023-10-20 09:18:28,285 - TensorboardLogger
|
65 |
+
2023-10-20 09:18:28,285 - LinearScheduler | warmup_fraction: '0.1'
|
66 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
67 |
+
2023-10-20 09:18:28,285 Final evaluation on model from best epoch (best-model.pt)
|
68 |
+
2023-10-20 09:18:28,285 - metric: "('micro avg', 'f1-score')"
|
69 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
70 |
+
2023-10-20 09:18:28,285 Computation:
|
71 |
+
2023-10-20 09:18:28,285 - compute on device: cuda:0
|
72 |
+
2023-10-20 09:18:28,285 - embedding storage: none
|
73 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
74 |
+
2023-10-20 09:18:28,285 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
|
75 |
+
2023-10-20 09:18:28,285 ----------------------------------------------------------------------------------------------------
|
76 |
+
2023-10-20 09:18:28,286 ----------------------------------------------------------------------------------------------------
|
77 |
+
2023-10-20 09:18:28,286 Logging anything other than scalars to TensorBoard is currently not supported.
|
78 |
+
2023-10-20 09:18:30,058 epoch 1 - iter 77/773 - loss 3.29697785 - time (sec): 1.77 - samples/sec: 7168.00 - lr: 0.000005 - momentum: 0.000000
|
79 |
+
2023-10-20 09:18:31,992 epoch 1 - iter 154/773 - loss 2.98890475 - time (sec): 3.71 - samples/sec: 6576.90 - lr: 0.000010 - momentum: 0.000000
|
80 |
+
2023-10-20 09:18:33,803 epoch 1 - iter 231/773 - loss 2.52454647 - time (sec): 5.52 - samples/sec: 6624.09 - lr: 0.000015 - momentum: 0.000000
|
81 |
+
2023-10-20 09:18:35,611 epoch 1 - iter 308/773 - loss 2.02302739 - time (sec): 7.32 - samples/sec: 6736.79 - lr: 0.000020 - momentum: 0.000000
|
82 |
+
2023-10-20 09:18:37,338 epoch 1 - iter 385/773 - loss 1.67463555 - time (sec): 9.05 - samples/sec: 6790.49 - lr: 0.000025 - momentum: 0.000000
|
83 |
+
2023-10-20 09:18:39,053 epoch 1 - iter 462/773 - loss 1.45168116 - time (sec): 10.77 - samples/sec: 6786.86 - lr: 0.000030 - momentum: 0.000000
|
84 |
+
2023-10-20 09:18:40,795 epoch 1 - iter 539/773 - loss 1.27870844 - time (sec): 12.51 - samples/sec: 6856.46 - lr: 0.000035 - momentum: 0.000000
|
85 |
+
2023-10-20 09:18:42,569 epoch 1 - iter 616/773 - loss 1.14349474 - time (sec): 14.28 - samples/sec: 6915.75 - lr: 0.000040 - momentum: 0.000000
|
86 |
+
2023-10-20 09:18:44,300 epoch 1 - iter 693/773 - loss 1.04649070 - time (sec): 16.01 - samples/sec: 6911.30 - lr: 0.000045 - momentum: 0.000000
|
87 |
+
2023-10-20 09:18:46,008 epoch 1 - iter 770/773 - loss 0.96192728 - time (sec): 17.72 - samples/sec: 6982.19 - lr: 0.000050 - momentum: 0.000000
|
88 |
+
2023-10-20 09:18:46,078 ----------------------------------------------------------------------------------------------------
|
89 |
+
2023-10-20 09:18:46,078 EPOCH 1 done: loss 0.9579 - lr: 0.000050
|
90 |
+
2023-10-20 09:18:47,081 DEV : loss 0.13065889477729797 - f1-score (micro avg) 0.0
|
91 |
+
2023-10-20 09:18:47,093 ----------------------------------------------------------------------------------------------------
|
92 |
+
2023-10-20 09:18:48,821 epoch 2 - iter 77/773 - loss 0.21812324 - time (sec): 1.73 - samples/sec: 7194.59 - lr: 0.000049 - momentum: 0.000000
|
93 |
+
2023-10-20 09:18:50,518 epoch 2 - iter 154/773 - loss 0.20906091 - time (sec): 3.42 - samples/sec: 7000.84 - lr: 0.000049 - momentum: 0.000000
|
94 |
+
2023-10-20 09:18:52,209 epoch 2 - iter 231/773 - loss 0.20993493 - time (sec): 5.12 - samples/sec: 6931.96 - lr: 0.000048 - momentum: 0.000000
|
95 |
+
2023-10-20 09:18:54,042 epoch 2 - iter 308/773 - loss 0.19690084 - time (sec): 6.95 - samples/sec: 6958.80 - lr: 0.000048 - momentum: 0.000000
|
96 |
+
2023-10-20 09:18:55,800 epoch 2 - iter 385/773 - loss 0.19499084 - time (sec): 8.71 - samples/sec: 7026.30 - lr: 0.000047 - momentum: 0.000000
|
97 |
+
2023-10-20 09:18:57,611 epoch 2 - iter 462/773 - loss 0.19104238 - time (sec): 10.52 - samples/sec: 6931.75 - lr: 0.000047 - momentum: 0.000000
|
98 |
+
2023-10-20 09:18:59,427 epoch 2 - iter 539/773 - loss 0.18943072 - time (sec): 12.33 - samples/sec: 6878.89 - lr: 0.000046 - momentum: 0.000000
|
99 |
+
2023-10-20 09:19:01,231 epoch 2 - iter 616/773 - loss 0.18586711 - time (sec): 14.14 - samples/sec: 6897.61 - lr: 0.000046 - momentum: 0.000000
|
100 |
+
2023-10-20 09:19:03,004 epoch 2 - iter 693/773 - loss 0.18459343 - time (sec): 15.91 - samples/sec: 6903.21 - lr: 0.000045 - momentum: 0.000000
|
101 |
+
2023-10-20 09:19:04,772 epoch 2 - iter 770/773 - loss 0.18021271 - time (sec): 17.68 - samples/sec: 6991.26 - lr: 0.000044 - momentum: 0.000000
|
102 |
+
2023-10-20 09:19:04,847 ----------------------------------------------------------------------------------------------------
|
103 |
+
2023-10-20 09:19:04,848 EPOCH 2 done: loss 0.1796 - lr: 0.000044
|
104 |
+
2023-10-20 09:19:06,215 DEV : loss 0.08806052803993225 - f1-score (micro avg) 0.4817
|
105 |
+
2023-10-20 09:19:06,227 saving best model
|
106 |
+
2023-10-20 09:19:06,256 ----------------------------------------------------------------------------------------------------
|
107 |
+
2023-10-20 09:19:08,034 epoch 3 - iter 77/773 - loss 0.16021178 - time (sec): 1.78 - samples/sec: 6437.36 - lr: 0.000044 - momentum: 0.000000
|
108 |
+
2023-10-20 09:19:09,769 epoch 3 - iter 154/773 - loss 0.14807212 - time (sec): 3.51 - samples/sec: 6858.33 - lr: 0.000043 - momentum: 0.000000
|
109 |
+
2023-10-20 09:19:11,509 epoch 3 - iter 231/773 - loss 0.14019763 - time (sec): 5.25 - samples/sec: 6941.49 - lr: 0.000043 - momentum: 0.000000
|
110 |
+
2023-10-20 09:19:13,236 epoch 3 - iter 308/773 - loss 0.14847424 - time (sec): 6.98 - samples/sec: 7082.25 - lr: 0.000042 - momentum: 0.000000
|
111 |
+
2023-10-20 09:19:14,934 epoch 3 - iter 385/773 - loss 0.14709744 - time (sec): 8.68 - samples/sec: 7070.55 - lr: 0.000042 - momentum: 0.000000
|
112 |
+
2023-10-20 09:19:16,681 epoch 3 - iter 462/773 - loss 0.14818828 - time (sec): 10.42 - samples/sec: 7183.86 - lr: 0.000041 - momentum: 0.000000
|
113 |
+
2023-10-20 09:19:18,432 epoch 3 - iter 539/773 - loss 0.14929835 - time (sec): 12.18 - samples/sec: 7178.10 - lr: 0.000041 - momentum: 0.000000
|
114 |
+
2023-10-20 09:19:20,162 epoch 3 - iter 616/773 - loss 0.14786552 - time (sec): 13.91 - samples/sec: 7189.40 - lr: 0.000040 - momentum: 0.000000
|
115 |
+
2023-10-20 09:19:21,899 epoch 3 - iter 693/773 - loss 0.14779447 - time (sec): 15.64 - samples/sec: 7105.63 - lr: 0.000039 - momentum: 0.000000
|
116 |
+
2023-10-20 09:19:23,605 epoch 3 - iter 770/773 - loss 0.14693652 - time (sec): 17.35 - samples/sec: 7129.47 - lr: 0.000039 - momentum: 0.000000
|
117 |
+
2023-10-20 09:19:23,676 ----------------------------------------------------------------------------------------------------
|
118 |
+
2023-10-20 09:19:23,676 EPOCH 3 done: loss 0.1467 - lr: 0.000039
|
119 |
+
2023-10-20 09:19:24,745 DEV : loss 0.07945284247398376 - f1-score (micro avg) 0.585
|
120 |
+
2023-10-20 09:19:24,756 saving best model
|
121 |
+
2023-10-20 09:19:24,790 ----------------------------------------------------------------------------------------------------
|
122 |
+
2023-10-20 09:19:26,577 epoch 4 - iter 77/773 - loss 0.13996426 - time (sec): 1.79 - samples/sec: 7057.97 - lr: 0.000038 - momentum: 0.000000
|
123 |
+
2023-10-20 09:19:28,330 epoch 4 - iter 154/773 - loss 0.13144568 - time (sec): 3.54 - samples/sec: 7020.35 - lr: 0.000038 - momentum: 0.000000
|
124 |
+
2023-10-20 09:19:30,061 epoch 4 - iter 231/773 - loss 0.13656365 - time (sec): 5.27 - samples/sec: 6788.28 - lr: 0.000037 - momentum: 0.000000
|
125 |
+
2023-10-20 09:19:31,745 epoch 4 - iter 308/773 - loss 0.13712233 - time (sec): 6.95 - samples/sec: 6967.80 - lr: 0.000037 - momentum: 0.000000
|
126 |
+
2023-10-20 09:19:33,517 epoch 4 - iter 385/773 - loss 0.13771739 - time (sec): 8.73 - samples/sec: 6955.05 - lr: 0.000036 - momentum: 0.000000
|
127 |
+
2023-10-20 09:19:35,269 epoch 4 - iter 462/773 - loss 0.13408346 - time (sec): 10.48 - samples/sec: 6958.02 - lr: 0.000036 - momentum: 0.000000
|
128 |
+
2023-10-20 09:19:37,000 epoch 4 - iter 539/773 - loss 0.13073922 - time (sec): 12.21 - samples/sec: 7056.03 - lr: 0.000035 - momentum: 0.000000
|
129 |
+
2023-10-20 09:19:38,795 epoch 4 - iter 616/773 - loss 0.13003178 - time (sec): 14.00 - samples/sec: 7078.88 - lr: 0.000034 - momentum: 0.000000
|
130 |
+
2023-10-20 09:19:40,490 epoch 4 - iter 693/773 - loss 0.13006617 - time (sec): 15.70 - samples/sec: 7082.33 - lr: 0.000034 - momentum: 0.000000
|
131 |
+
2023-10-20 09:19:42,234 epoch 4 - iter 770/773 - loss 0.12994693 - time (sec): 17.44 - samples/sec: 7100.14 - lr: 0.000033 - momentum: 0.000000
|
132 |
+
2023-10-20 09:19:42,298 ----------------------------------------------------------------------------------------------------
|
133 |
+
2023-10-20 09:19:42,298 EPOCH 4 done: loss 0.1299 - lr: 0.000033
|
134 |
+
2023-10-20 09:19:43,375 DEV : loss 0.07809021323919296 - f1-score (micro avg) 0.6071
|
135 |
+
2023-10-20 09:19:43,386 saving best model
|
136 |
+
2023-10-20 09:19:43,425 ----------------------------------------------------------------------------------------------------
|
137 |
+
2023-10-20 09:19:45,188 epoch 5 - iter 77/773 - loss 0.11117031 - time (sec): 1.76 - samples/sec: 6996.81 - lr: 0.000033 - momentum: 0.000000
|
138 |
+
2023-10-20 09:19:46,900 epoch 5 - iter 154/773 - loss 0.11764714 - time (sec): 3.47 - samples/sec: 6894.04 - lr: 0.000032 - momentum: 0.000000
|
139 |
+
2023-10-20 09:19:48,635 epoch 5 - iter 231/773 - loss 0.11991202 - time (sec): 5.21 - samples/sec: 6905.69 - lr: 0.000032 - momentum: 0.000000
|
140 |
+
2023-10-20 09:19:50,432 epoch 5 - iter 308/773 - loss 0.11700014 - time (sec): 7.01 - samples/sec: 7024.72 - lr: 0.000031 - momentum: 0.000000
|
141 |
+
2023-10-20 09:19:52,197 epoch 5 - iter 385/773 - loss 0.11617792 - time (sec): 8.77 - samples/sec: 7091.97 - lr: 0.000031 - momentum: 0.000000
|
142 |
+
2023-10-20 09:19:53,901 epoch 5 - iter 462/773 - loss 0.11525526 - time (sec): 10.48 - samples/sec: 7097.11 - lr: 0.000030 - momentum: 0.000000
|
143 |
+
2023-10-20 09:19:55,632 epoch 5 - iter 539/773 - loss 0.11333040 - time (sec): 12.21 - samples/sec: 7074.53 - lr: 0.000029 - momentum: 0.000000
|
144 |
+
2023-10-20 09:19:57,353 epoch 5 - iter 616/773 - loss 0.11550300 - time (sec): 13.93 - samples/sec: 7091.84 - lr: 0.000029 - momentum: 0.000000
|
145 |
+
2023-10-20 09:19:59,064 epoch 5 - iter 693/773 - loss 0.11629394 - time (sec): 15.64 - samples/sec: 7154.16 - lr: 0.000028 - momentum: 0.000000
|
146 |
+
2023-10-20 09:20:00,821 epoch 5 - iter 770/773 - loss 0.11699897 - time (sec): 17.40 - samples/sec: 7117.38 - lr: 0.000028 - momentum: 0.000000
|
147 |
+
2023-10-20 09:20:00,890 ----------------------------------------------------------------------------------------------------
|
148 |
+
2023-10-20 09:20:00,890 EPOCH 5 done: loss 0.1169 - lr: 0.000028
|
149 |
+
2023-10-20 09:20:01,993 DEV : loss 0.07527422904968262 - f1-score (micro avg) 0.5973
|
150 |
+
2023-10-20 09:20:02,004 ----------------------------------------------------------------------------------------------------
|
151 |
+
2023-10-20 09:20:03,679 epoch 6 - iter 77/773 - loss 0.09373771 - time (sec): 1.67 - samples/sec: 7129.91 - lr: 0.000027 - momentum: 0.000000
|
152 |
+
2023-10-20 09:20:05,341 epoch 6 - iter 154/773 - loss 0.10168393 - time (sec): 3.34 - samples/sec: 7107.39 - lr: 0.000027 - momentum: 0.000000
|
153 |
+
2023-10-20 09:20:07,029 epoch 6 - iter 231/773 - loss 0.11169160 - time (sec): 5.02 - samples/sec: 7123.67 - lr: 0.000026 - momentum: 0.000000
|
154 |
+
2023-10-20 09:20:08,763 epoch 6 - iter 308/773 - loss 0.11308050 - time (sec): 6.76 - samples/sec: 7205.74 - lr: 0.000026 - momentum: 0.000000
|
155 |
+
2023-10-20 09:20:10,476 epoch 6 - iter 385/773 - loss 0.11734393 - time (sec): 8.47 - samples/sec: 7119.05 - lr: 0.000025 - momentum: 0.000000
|
156 |
+
2023-10-20 09:20:12,242 epoch 6 - iter 462/773 - loss 0.11359539 - time (sec): 10.24 - samples/sec: 7161.69 - lr: 0.000024 - momentum: 0.000000
|
157 |
+
2023-10-20 09:20:13,952 epoch 6 - iter 539/773 - loss 0.11053055 - time (sec): 11.95 - samples/sec: 7179.03 - lr: 0.000024 - momentum: 0.000000
|
158 |
+
2023-10-20 09:20:15,718 epoch 6 - iter 616/773 - loss 0.10958303 - time (sec): 13.71 - samples/sec: 7213.13 - lr: 0.000023 - momentum: 0.000000
|
159 |
+
2023-10-20 09:20:17,429 epoch 6 - iter 693/773 - loss 0.10856611 - time (sec): 15.42 - samples/sec: 7165.92 - lr: 0.000023 - momentum: 0.000000
|
160 |
+
2023-10-20 09:20:19,168 epoch 6 - iter 770/773 - loss 0.10997793 - time (sec): 17.16 - samples/sec: 7211.89 - lr: 0.000022 - momentum: 0.000000
|
161 |
+
2023-10-20 09:20:19,240 ----------------------------------------------------------------------------------------------------
|
162 |
+
2023-10-20 09:20:19,241 EPOCH 6 done: loss 0.1098 - lr: 0.000022
|
163 |
+
2023-10-20 09:20:20,340 DEV : loss 0.07457771897315979 - f1-score (micro avg) 0.6144
|
164 |
+
2023-10-20 09:20:20,354 saving best model
|
165 |
+
2023-10-20 09:20:20,394 ----------------------------------------------------------------------------------------------------
|
166 |
+
2023-10-20 09:20:22,182 epoch 7 - iter 77/773 - loss 0.10104822 - time (sec): 1.79 - samples/sec: 7514.85 - lr: 0.000022 - momentum: 0.000000
|
167 |
+
2023-10-20 09:20:23,898 epoch 7 - iter 154/773 - loss 0.09821556 - time (sec): 3.50 - samples/sec: 7100.36 - lr: 0.000021 - momentum: 0.000000
|
168 |
+
2023-10-20 09:20:25,626 epoch 7 - iter 231/773 - loss 0.09548090 - time (sec): 5.23 - samples/sec: 7242.33 - lr: 0.000021 - momentum: 0.000000
|
169 |
+
2023-10-20 09:20:27,321 epoch 7 - iter 308/773 - loss 0.10355270 - time (sec): 6.93 - samples/sec: 7143.99 - lr: 0.000020 - momentum: 0.000000
|
170 |
+
2023-10-20 09:20:29,117 epoch 7 - iter 385/773 - loss 0.10438038 - time (sec): 8.72 - samples/sec: 7124.85 - lr: 0.000019 - momentum: 0.000000
|
171 |
+
2023-10-20 09:20:30,854 epoch 7 - iter 462/773 - loss 0.10313345 - time (sec): 10.46 - samples/sec: 7148.72 - lr: 0.000019 - momentum: 0.000000
|
172 |
+
2023-10-20 09:20:32,639 epoch 7 - iter 539/773 - loss 0.10557270 - time (sec): 12.24 - samples/sec: 7134.59 - lr: 0.000018 - momentum: 0.000000
|
173 |
+
2023-10-20 09:20:34,316 epoch 7 - iter 616/773 - loss 0.10463863 - time (sec): 13.92 - samples/sec: 7183.24 - lr: 0.000018 - momentum: 0.000000
|
174 |
+
2023-10-20 09:20:36,084 epoch 7 - iter 693/773 - loss 0.10402035 - time (sec): 15.69 - samples/sec: 7119.43 - lr: 0.000017 - momentum: 0.000000
|
175 |
+
2023-10-20 09:20:37,828 epoch 7 - iter 770/773 - loss 0.10392693 - time (sec): 17.43 - samples/sec: 7102.19 - lr: 0.000017 - momentum: 0.000000
|
176 |
+
2023-10-20 09:20:37,899 ----------------------------------------------------------------------------------------------------
|
177 |
+
2023-10-20 09:20:37,899 EPOCH 7 done: loss 0.1037 - lr: 0.000017
|
178 |
+
2023-10-20 09:20:39,024 DEV : loss 0.07657597213983536 - f1-score (micro avg) 0.6242
|
179 |
+
2023-10-20 09:20:39,037 saving best model
|
180 |
+
2023-10-20 09:20:39,075 ----------------------------------------------------------------------------------------------------
|
181 |
+
2023-10-20 09:20:40,803 epoch 8 - iter 77/773 - loss 0.08347295 - time (sec): 1.73 - samples/sec: 7045.81 - lr: 0.000016 - momentum: 0.000000
|
182 |
+
2023-10-20 09:20:42,539 epoch 8 - iter 154/773 - loss 0.10176786 - time (sec): 3.46 - samples/sec: 7193.34 - lr: 0.000016 - momentum: 0.000000
|
183 |
+
2023-10-20 09:20:44,261 epoch 8 - iter 231/773 - loss 0.10219115 - time (sec): 5.19 - samples/sec: 7117.05 - lr: 0.000015 - momentum: 0.000000
|
184 |
+
2023-10-20 09:20:45,993 epoch 8 - iter 308/773 - loss 0.09661994 - time (sec): 6.92 - samples/sec: 7120.96 - lr: 0.000014 - momentum: 0.000000
|
185 |
+
2023-10-20 09:20:47,714 epoch 8 - iter 385/773 - loss 0.09443349 - time (sec): 8.64 - samples/sec: 7214.99 - lr: 0.000014 - momentum: 0.000000
|
186 |
+
2023-10-20 09:20:49,480 epoch 8 - iter 462/773 - loss 0.09714750 - time (sec): 10.40 - samples/sec: 7273.85 - lr: 0.000013 - momentum: 0.000000
|
187 |
+
2023-10-20 09:20:51,177 epoch 8 - iter 539/773 - loss 0.09639649 - time (sec): 12.10 - samples/sec: 7201.04 - lr: 0.000013 - momentum: 0.000000
|
188 |
+
2023-10-20 09:20:52,899 epoch 8 - iter 616/773 - loss 0.09879490 - time (sec): 13.82 - samples/sec: 7136.22 - lr: 0.000012 - momentum: 0.000000
|
189 |
+
2023-10-20 09:20:54,622 epoch 8 - iter 693/773 - loss 0.09745774 - time (sec): 15.55 - samples/sec: 7128.81 - lr: 0.000012 - momentum: 0.000000
|
190 |
+
2023-10-20 09:20:56,382 epoch 8 - iter 770/773 - loss 0.09749713 - time (sec): 17.31 - samples/sec: 7163.01 - lr: 0.000011 - momentum: 0.000000
|
191 |
+
2023-10-20 09:20:56,439 ----------------------------------------------------------------------------------------------------
|
192 |
+
2023-10-20 09:20:56,439 EPOCH 8 done: loss 0.0973 - lr: 0.000011
|
193 |
+
2023-10-20 09:20:57,540 DEV : loss 0.07944915443658829 - f1-score (micro avg) 0.6269
|
194 |
+
2023-10-20 09:20:57,552 saving best model
|
195 |
+
2023-10-20 09:20:57,590 ----------------------------------------------------------------------------------------------------
|
196 |
+
2023-10-20 09:20:59,260 epoch 9 - iter 77/773 - loss 0.09459646 - time (sec): 1.67 - samples/sec: 7330.85 - lr: 0.000011 - momentum: 0.000000
|
197 |
+
2023-10-20 09:21:00,859 epoch 9 - iter 154/773 - loss 0.09513909 - time (sec): 3.27 - samples/sec: 7555.16 - lr: 0.000010 - momentum: 0.000000
|
198 |
+
2023-10-20 09:21:02,459 epoch 9 - iter 231/773 - loss 0.08891959 - time (sec): 4.87 - samples/sec: 7837.97 - lr: 0.000009 - momentum: 0.000000
|
199 |
+
2023-10-20 09:21:04,135 epoch 9 - iter 308/773 - loss 0.09023339 - time (sec): 6.54 - samples/sec: 7649.30 - lr: 0.000009 - momentum: 0.000000
|
200 |
+
2023-10-20 09:21:05,867 epoch 9 - iter 385/773 - loss 0.09340261 - time (sec): 8.28 - samples/sec: 7652.07 - lr: 0.000008 - momentum: 0.000000
|
201 |
+
2023-10-20 09:21:07,610 epoch 9 - iter 462/773 - loss 0.09643093 - time (sec): 10.02 - samples/sec: 7510.55 - lr: 0.000008 - momentum: 0.000000
|
202 |
+
2023-10-20 09:21:09,362 epoch 9 - iter 539/773 - loss 0.09664935 - time (sec): 11.77 - samples/sec: 7470.84 - lr: 0.000007 - momentum: 0.000000
|
203 |
+
2023-10-20 09:21:11,036 epoch 9 - iter 616/773 - loss 0.09738019 - time (sec): 13.45 - samples/sec: 7447.59 - lr: 0.000007 - momentum: 0.000000
|
204 |
+
2023-10-20 09:21:12,730 epoch 9 - iter 693/773 - loss 0.09569268 - time (sec): 15.14 - samples/sec: 7368.56 - lr: 0.000006 - momentum: 0.000000
|
205 |
+
2023-10-20 09:21:14,449 epoch 9 - iter 770/773 - loss 0.09441439 - time (sec): 16.86 - samples/sec: 7348.71 - lr: 0.000006 - momentum: 0.000000
|
206 |
+
2023-10-20 09:21:14,509 ----------------------------------------------------------------------------------------------------
|
207 |
+
2023-10-20 09:21:14,509 EPOCH 9 done: loss 0.0943 - lr: 0.000006
|
208 |
+
2023-10-20 09:21:15,576 DEV : loss 0.08020081371068954 - f1-score (micro avg) 0.6476
|
209 |
+
2023-10-20 09:21:15,587 saving best model
|
210 |
+
2023-10-20 09:21:15,626 ----------------------------------------------------------------------------------------------------
|
211 |
+
2023-10-20 09:21:17,352 epoch 10 - iter 77/773 - loss 0.10683426 - time (sec): 1.73 - samples/sec: 6965.15 - lr: 0.000005 - momentum: 0.000000
|
212 |
+
2023-10-20 09:21:19,118 epoch 10 - iter 154/773 - loss 0.09922985 - time (sec): 3.49 - samples/sec: 7124.64 - lr: 0.000005 - momentum: 0.000000
|
213 |
+
2023-10-20 09:21:20,969 epoch 10 - iter 231/773 - loss 0.09606770 - time (sec): 5.34 - samples/sec: 7135.38 - lr: 0.000004 - momentum: 0.000000
|
214 |
+
2023-10-20 09:21:22,727 epoch 10 - iter 308/773 - loss 0.09168936 - time (sec): 7.10 - samples/sec: 7163.36 - lr: 0.000003 - momentum: 0.000000
|
215 |
+
2023-10-20 09:21:24,454 epoch 10 - iter 385/773 - loss 0.09319490 - time (sec): 8.83 - samples/sec: 7145.89 - lr: 0.000003 - momentum: 0.000000
|
216 |
+
2023-10-20 09:21:26,193 epoch 10 - iter 462/773 - loss 0.09108964 - time (sec): 10.57 - samples/sec: 7122.69 - lr: 0.000002 - momentum: 0.000000
|
217 |
+
2023-10-20 09:21:27,920 epoch 10 - iter 539/773 - loss 0.08863410 - time (sec): 12.29 - samples/sec: 7160.35 - lr: 0.000002 - momentum: 0.000000
|
218 |
+
2023-10-20 09:21:29,676 epoch 10 - iter 616/773 - loss 0.08839821 - time (sec): 14.05 - samples/sec: 7084.18 - lr: 0.000001 - momentum: 0.000000
|
219 |
+
2023-10-20 09:21:31,407 epoch 10 - iter 693/773 - loss 0.09194621 - time (sec): 15.78 - samples/sec: 7085.52 - lr: 0.000001 - momentum: 0.000000
|
220 |
+
2023-10-20 09:21:33,142 epoch 10 - iter 770/773 - loss 0.09345324 - time (sec): 17.52 - samples/sec: 7078.58 - lr: 0.000000 - momentum: 0.000000
|
221 |
+
2023-10-20 09:21:33,207 ----------------------------------------------------------------------------------------------------
|
222 |
+
2023-10-20 09:21:33,207 EPOCH 10 done: loss 0.0933 - lr: 0.000000
|
223 |
+
2023-10-20 09:21:34,289 DEV : loss 0.08138395845890045 - f1-score (micro avg) 0.6491
|
224 |
+
2023-10-20 09:21:34,302 saving best model
|
225 |
+
2023-10-20 09:21:34,370 ----------------------------------------------------------------------------------------------------
|
226 |
+
2023-10-20 09:21:34,371 Loading model from best epoch ...
|
227 |
+
2023-10-20 09:21:34,443 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
|
228 |
+
2023-10-20 09:21:37,354
|
229 |
+
Results:
|
230 |
+
- F-score (micro) 0.5866
|
231 |
+
- F-score (macro) 0.3173
|
232 |
+
- Accuracy 0.4314
|
233 |
+
|
234 |
+
By class:
|
235 |
+
precision recall f1-score support
|
236 |
+
|
237 |
+
LOC 0.6274 0.6818 0.6535 946
|
238 |
+
BUILDING 0.3400 0.0919 0.1447 185
|
239 |
+
STREET 0.5556 0.0893 0.1538 56
|
240 |
+
|
241 |
+
micro avg 0.6136 0.5619 0.5866 1187
|
242 |
+
macro avg 0.5077 0.2877 0.3173 1187
|
243 |
+
weighted avg 0.5792 0.5619 0.5506 1187
|
244 |
+
|
245 |
+
2023-10-20 09:21:37,354 ----------------------------------------------------------------------------------------------------
|