Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
89c5c67
·
1 Parent(s): 83e3fe2

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 +246 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff98a735ffcd3727123f67028771e9b65a0410377f4568d6bb1b612372b031a
3
+ size 443335879
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 16:33:44 0.0000 0.4771 0.1404 0.6390 0.7532 0.6914 0.5601
3
+ 2 16:35:05 0.0000 0.1364 0.1494 0.6751 0.8104 0.7366 0.6086
4
+ 3 16:36:26 0.0000 0.0912 0.1711 0.7682 0.7841 0.7761 0.6630
5
+ 4 16:37:47 0.0000 0.0647 0.2201 0.7341 0.8173 0.7734 0.6582
6
+ 5 16:39:09 0.0000 0.0466 0.1859 0.7751 0.8093 0.7918 0.6916
7
+ 6 16:40:30 0.0000 0.0353 0.2059 0.7870 0.8001 0.7935 0.6926
8
+ 7 16:41:52 0.0000 0.0226 0.2367 0.7784 0.8167 0.7971 0.6896
9
+ 8 16:43:13 0.0000 0.0158 0.2536 0.7852 0.8121 0.7984 0.6958
10
+ 9 16:44:35 0.0000 0.0100 0.2553 0.7919 0.8127 0.8021 0.7021
11
+ 10 16:45:57 0.0000 0.0067 0.2592 0.7992 0.8184 0.8087 0.7106
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 16:32:27,478 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 16:32:27,479 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=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 16:32:27,479 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 16:32:27,480 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
52
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
53
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 16:32:27,480 Train: 5901 sentences
55
+ 2023-10-13 16:32:27,480 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 16:32:27,480 Training Params:
58
+ 2023-10-13 16:32:27,480 - learning_rate: "5e-05"
59
+ 2023-10-13 16:32:27,480 - mini_batch_size: "4"
60
+ 2023-10-13 16:32:27,480 - max_epochs: "10"
61
+ 2023-10-13 16:32:27,480 - shuffle: "True"
62
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 16:32:27,480 Plugins:
64
+ 2023-10-13 16:32:27,480 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 16:32:27,480 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 16:32:27,480 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 16:32:27,480 Computation:
70
+ 2023-10-13 16:32:27,480 - compute on device: cuda:0
71
+ 2023-10-13 16:32:27,480 - embedding storage: none
72
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 16:32:27,480 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
74
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 16:32:27,480 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 16:32:34,656 epoch 1 - iter 147/1476 - loss 2.19264043 - time (sec): 7.17 - samples/sec: 2468.65 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 16:32:41,887 epoch 1 - iter 294/1476 - loss 1.34715324 - time (sec): 14.41 - samples/sec: 2494.63 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 16:32:48,820 epoch 1 - iter 441/1476 - loss 1.03252218 - time (sec): 21.34 - samples/sec: 2436.06 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 16:32:55,839 epoch 1 - iter 588/1476 - loss 0.84618778 - time (sec): 28.36 - samples/sec: 2423.52 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 16:33:03,052 epoch 1 - iter 735/1476 - loss 0.73617883 - time (sec): 35.57 - samples/sec: 2406.00 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-13 16:33:10,075 epoch 1 - iter 882/1476 - loss 0.65221352 - time (sec): 42.59 - samples/sec: 2401.55 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-13 16:33:16,986 epoch 1 - iter 1029/1476 - loss 0.59171549 - time (sec): 49.50 - samples/sec: 2395.74 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-13 16:33:23,748 epoch 1 - iter 1176/1476 - loss 0.54902197 - time (sec): 56.27 - samples/sec: 2370.02 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-13 16:33:30,731 epoch 1 - iter 1323/1476 - loss 0.50983066 - time (sec): 63.25 - samples/sec: 2366.30 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-13 16:33:37,571 epoch 1 - iter 1470/1476 - loss 0.47806023 - time (sec): 70.09 - samples/sec: 2366.46 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-13 16:33:37,841 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 16:33:37,841 EPOCH 1 done: loss 0.4771 - lr: 0.000050
88
+ 2023-10-13 16:33:44,025 DEV : loss 0.14038856327533722 - f1-score (micro avg) 0.6914
89
+ 2023-10-13 16:33:44,053 saving best model
90
+ 2023-10-13 16:33:44,489 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 16:33:51,114 epoch 2 - iter 147/1476 - loss 0.13041987 - time (sec): 6.62 - samples/sec: 2298.32 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 16:33:57,959 epoch 2 - iter 294/1476 - loss 0.13920225 - time (sec): 13.47 - samples/sec: 2333.22 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 16:34:04,703 epoch 2 - iter 441/1476 - loss 0.13806486 - time (sec): 20.21 - samples/sec: 2363.50 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 16:34:11,574 epoch 2 - iter 588/1476 - loss 0.13521110 - time (sec): 27.08 - samples/sec: 2354.34 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 16:34:18,376 epoch 2 - iter 735/1476 - loss 0.14108629 - time (sec): 33.89 - samples/sec: 2331.03 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 16:34:25,372 epoch 2 - iter 882/1476 - loss 0.13917247 - time (sec): 40.88 - samples/sec: 2349.90 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 16:34:32,628 epoch 2 - iter 1029/1476 - loss 0.13722354 - time (sec): 48.14 - samples/sec: 2377.81 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 16:34:39,515 epoch 2 - iter 1176/1476 - loss 0.13237447 - time (sec): 55.02 - samples/sec: 2379.51 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 16:34:46,566 epoch 2 - iter 1323/1476 - loss 0.13528695 - time (sec): 62.08 - samples/sec: 2384.90 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 16:34:53,726 epoch 2 - iter 1470/1476 - loss 0.13631749 - time (sec): 69.24 - samples/sec: 2391.96 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-13 16:34:54,002 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 16:34:54,002 EPOCH 2 done: loss 0.1364 - lr: 0.000044
103
+ 2023-10-13 16:35:05,260 DEV : loss 0.14942534267902374 - f1-score (micro avg) 0.7366
104
+ 2023-10-13 16:35:05,289 saving best model
105
+ 2023-10-13 16:35:05,779 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 16:35:12,635 epoch 3 - iter 147/1476 - loss 0.07591353 - time (sec): 6.85 - samples/sec: 2265.56 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 16:35:19,528 epoch 3 - iter 294/1476 - loss 0.09227817 - time (sec): 13.74 - samples/sec: 2354.13 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 16:35:26,354 epoch 3 - iter 441/1476 - loss 0.09626614 - time (sec): 20.57 - samples/sec: 2363.80 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 16:35:33,095 epoch 3 - iter 588/1476 - loss 0.09646343 - time (sec): 27.31 - samples/sec: 2347.82 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 16:35:40,240 epoch 3 - iter 735/1476 - loss 0.09416145 - time (sec): 34.45 - samples/sec: 2367.35 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 16:35:47,371 epoch 3 - iter 882/1476 - loss 0.09456799 - time (sec): 41.59 - samples/sec: 2406.31 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 16:35:54,299 epoch 3 - iter 1029/1476 - loss 0.09149587 - time (sec): 48.51 - samples/sec: 2393.68 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 16:36:01,363 epoch 3 - iter 1176/1476 - loss 0.09190785 - time (sec): 55.58 - samples/sec: 2410.90 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 16:36:08,187 epoch 3 - iter 1323/1476 - loss 0.09115192 - time (sec): 62.40 - samples/sec: 2407.82 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-13 16:36:15,108 epoch 3 - iter 1470/1476 - loss 0.09131695 - time (sec): 69.32 - samples/sec: 2391.98 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 16:36:15,376 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 16:36:15,376 EPOCH 3 done: loss 0.0912 - lr: 0.000039
118
+ 2023-10-13 16:36:26,447 DEV : loss 0.17109665274620056 - f1-score (micro avg) 0.7761
119
+ 2023-10-13 16:36:26,476 saving best model
120
+ 2023-10-13 16:36:27,050 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 16:36:33,918 epoch 4 - iter 147/1476 - loss 0.06448851 - time (sec): 6.86 - samples/sec: 2220.09 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 16:36:40,610 epoch 4 - iter 294/1476 - loss 0.05935983 - time (sec): 13.56 - samples/sec: 2294.42 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 16:36:47,491 epoch 4 - iter 441/1476 - loss 0.06577537 - time (sec): 20.44 - samples/sec: 2339.67 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 16:36:54,183 epoch 4 - iter 588/1476 - loss 0.06370900 - time (sec): 27.13 - samples/sec: 2330.56 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 16:37:01,145 epoch 4 - iter 735/1476 - loss 0.06430938 - time (sec): 34.09 - samples/sec: 2344.21 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 16:37:08,310 epoch 4 - iter 882/1476 - loss 0.06262401 - time (sec): 41.26 - samples/sec: 2361.23 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 16:37:15,650 epoch 4 - iter 1029/1476 - loss 0.06226410 - time (sec): 48.60 - samples/sec: 2394.58 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 16:37:22,567 epoch 4 - iter 1176/1476 - loss 0.06322309 - time (sec): 55.51 - samples/sec: 2395.17 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-13 16:37:29,580 epoch 4 - iter 1323/1476 - loss 0.06623547 - time (sec): 62.53 - samples/sec: 2394.70 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 16:37:36,240 epoch 4 - iter 1470/1476 - loss 0.06439991 - time (sec): 69.18 - samples/sec: 2395.39 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 16:37:36,522 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 16:37:36,522 EPOCH 4 done: loss 0.0647 - lr: 0.000033
133
+ 2023-10-13 16:37:47,651 DEV : loss 0.22011879086494446 - f1-score (micro avg) 0.7734
134
+ 2023-10-13 16:37:47,680 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-13 16:37:54,663 epoch 5 - iter 147/1476 - loss 0.05406225 - time (sec): 6.98 - samples/sec: 2371.22 - lr: 0.000033 - momentum: 0.000000
136
+ 2023-10-13 16:38:02,070 epoch 5 - iter 294/1476 - loss 0.05659229 - time (sec): 14.39 - samples/sec: 2313.32 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-13 16:38:09,156 epoch 5 - iter 441/1476 - loss 0.05185982 - time (sec): 21.48 - samples/sec: 2344.21 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 16:38:15,969 epoch 5 - iter 588/1476 - loss 0.05025944 - time (sec): 28.29 - samples/sec: 2347.40 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-13 16:38:22,835 epoch 5 - iter 735/1476 - loss 0.04794011 - time (sec): 35.15 - samples/sec: 2348.11 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 16:38:29,650 epoch 5 - iter 882/1476 - loss 0.04879169 - time (sec): 41.97 - samples/sec: 2336.67 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-13 16:38:36,556 epoch 5 - iter 1029/1476 - loss 0.04784084 - time (sec): 48.88 - samples/sec: 2340.55 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-13 16:38:43,817 epoch 5 - iter 1176/1476 - loss 0.04785536 - time (sec): 56.14 - samples/sec: 2366.35 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-13 16:38:50,949 epoch 5 - iter 1323/1476 - loss 0.04673364 - time (sec): 63.27 - samples/sec: 2382.16 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-13 16:38:57,668 epoch 5 - iter 1470/1476 - loss 0.04668226 - time (sec): 69.99 - samples/sec: 2369.74 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 16:38:57,926 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-13 16:38:57,927 EPOCH 5 done: loss 0.0466 - lr: 0.000028
147
+ 2023-10-13 16:39:09,057 DEV : loss 0.18591712415218353 - f1-score (micro avg) 0.7918
148
+ 2023-10-13 16:39:09,086 saving best model
149
+ 2023-10-13 16:39:09,678 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 16:39:16,341 epoch 6 - iter 147/1476 - loss 0.02523404 - time (sec): 6.66 - samples/sec: 2241.56 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-13 16:39:23,617 epoch 6 - iter 294/1476 - loss 0.02890210 - time (sec): 13.94 - samples/sec: 2449.63 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 16:39:30,543 epoch 6 - iter 441/1476 - loss 0.03369659 - time (sec): 20.86 - samples/sec: 2447.46 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-13 16:39:37,495 epoch 6 - iter 588/1476 - loss 0.03450237 - time (sec): 27.81 - samples/sec: 2424.06 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 16:39:44,573 epoch 6 - iter 735/1476 - loss 0.03447603 - time (sec): 34.89 - samples/sec: 2434.04 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-13 16:39:51,749 epoch 6 - iter 882/1476 - loss 0.03728195 - time (sec): 42.07 - samples/sec: 2428.75 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-13 16:39:58,407 epoch 6 - iter 1029/1476 - loss 0.03609371 - time (sec): 48.73 - samples/sec: 2409.30 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-13 16:40:05,348 epoch 6 - iter 1176/1476 - loss 0.03396739 - time (sec): 55.67 - samples/sec: 2406.36 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-13 16:40:12,191 epoch 6 - iter 1323/1476 - loss 0.03505791 - time (sec): 62.51 - samples/sec: 2396.41 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 16:40:19,135 epoch 6 - iter 1470/1476 - loss 0.03535902 - time (sec): 69.45 - samples/sec: 2389.64 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-13 16:40:19,401 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 16:40:19,401 EPOCH 6 done: loss 0.0353 - lr: 0.000022
162
+ 2023-10-13 16:40:30,593 DEV : loss 0.20590120553970337 - f1-score (micro avg) 0.7935
163
+ 2023-10-13 16:40:30,622 saving best model
164
+ 2023-10-13 16:40:31,204 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 16:40:38,565 epoch 7 - iter 147/1476 - loss 0.01875450 - time (sec): 7.36 - samples/sec: 2324.91 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-13 16:40:45,309 epoch 7 - iter 294/1476 - loss 0.01827635 - time (sec): 14.10 - samples/sec: 2279.02 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 16:40:52,625 epoch 7 - iter 441/1476 - loss 0.02228262 - time (sec): 21.42 - samples/sec: 2360.36 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-13 16:41:00,112 epoch 7 - iter 588/1476 - loss 0.02120762 - time (sec): 28.91 - samples/sec: 2398.25 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-13 16:41:06,805 epoch 7 - iter 735/1476 - loss 0.02126680 - time (sec): 35.60 - samples/sec: 2370.88 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-13 16:41:13,433 epoch 7 - iter 882/1476 - loss 0.02140474 - time (sec): 42.23 - samples/sec: 2362.59 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-13 16:41:19,855 epoch 7 - iter 1029/1476 - loss 0.02223445 - time (sec): 48.65 - samples/sec: 2381.63 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 16:41:26,472 epoch 7 - iter 1176/1476 - loss 0.02219911 - time (sec): 55.26 - samples/sec: 2380.18 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-13 16:41:33,320 epoch 7 - iter 1323/1476 - loss 0.02216569 - time (sec): 62.11 - samples/sec: 2376.25 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 16:41:40,533 epoch 7 - iter 1470/1476 - loss 0.02249640 - time (sec): 69.33 - samples/sec: 2392.97 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-13 16:41:40,788 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 16:41:40,788 EPOCH 7 done: loss 0.0226 - lr: 0.000017
177
+ 2023-10-13 16:41:51,974 DEV : loss 0.23674637079238892 - f1-score (micro avg) 0.7971
178
+ 2023-10-13 16:41:52,003 saving best model
179
+ 2023-10-13 16:41:52,500 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 16:41:59,567 epoch 8 - iter 147/1476 - loss 0.01813003 - time (sec): 7.07 - samples/sec: 2377.41 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-13 16:42:06,585 epoch 8 - iter 294/1476 - loss 0.01758301 - time (sec): 14.08 - samples/sec: 2397.59 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-13 16:42:13,868 epoch 8 - iter 441/1476 - loss 0.02116504 - time (sec): 21.37 - samples/sec: 2488.85 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-13 16:42:20,522 epoch 8 - iter 588/1476 - loss 0.02109938 - time (sec): 28.02 - samples/sec: 2426.58 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-13 16:42:27,485 epoch 8 - iter 735/1476 - loss 0.01950654 - time (sec): 34.98 - samples/sec: 2394.96 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-13 16:42:34,305 epoch 8 - iter 882/1476 - loss 0.01842251 - time (sec): 41.80 - samples/sec: 2372.96 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-13 16:42:41,420 epoch 8 - iter 1029/1476 - loss 0.01674893 - time (sec): 48.92 - samples/sec: 2354.63 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-13 16:42:48,112 epoch 8 - iter 1176/1476 - loss 0.01663061 - time (sec): 55.61 - samples/sec: 2343.53 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-13 16:42:55,261 epoch 8 - iter 1323/1476 - loss 0.01632528 - time (sec): 62.76 - samples/sec: 2359.37 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-13 16:43:02,148 epoch 8 - iter 1470/1476 - loss 0.01581879 - time (sec): 69.65 - samples/sec: 2380.38 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-13 16:43:02,409 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 16:43:02,409 EPOCH 8 done: loss 0.0158 - lr: 0.000011
192
+ 2023-10-13 16:43:13,521 DEV : loss 0.25357791781425476 - f1-score (micro avg) 0.7984
193
+ 2023-10-13 16:43:13,550 saving best model
194
+ 2023-10-13 16:43:14,117 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-13 16:43:21,014 epoch 9 - iter 147/1476 - loss 0.00927471 - time (sec): 6.89 - samples/sec: 2259.68 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-13 16:43:28,062 epoch 9 - iter 294/1476 - loss 0.00809657 - time (sec): 13.94 - samples/sec: 2364.85 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-13 16:43:34,763 epoch 9 - iter 441/1476 - loss 0.00782182 - time (sec): 20.64 - samples/sec: 2353.66 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-13 16:43:41,562 epoch 9 - iter 588/1476 - loss 0.00861677 - time (sec): 27.44 - samples/sec: 2378.37 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-13 16:43:48,725 epoch 9 - iter 735/1476 - loss 0.00955088 - time (sec): 34.60 - samples/sec: 2408.79 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-13 16:43:55,520 epoch 9 - iter 882/1476 - loss 0.00855623 - time (sec): 41.40 - samples/sec: 2391.02 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-13 16:44:02,540 epoch 9 - iter 1029/1476 - loss 0.00809094 - time (sec): 48.42 - samples/sec: 2397.34 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-13 16:44:09,395 epoch 9 - iter 1176/1476 - loss 0.00852934 - time (sec): 55.27 - samples/sec: 2381.55 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-13 16:44:16,493 epoch 9 - iter 1323/1476 - loss 0.00844392 - time (sec): 62.37 - samples/sec: 2374.19 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-13 16:44:23,796 epoch 9 - iter 1470/1476 - loss 0.00997719 - time (sec): 69.67 - samples/sec: 2376.32 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-13 16:44:24,083 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 16:44:24,083 EPOCH 9 done: loss 0.0100 - lr: 0.000006
207
+ 2023-10-13 16:44:35,753 DEV : loss 0.25528380274772644 - f1-score (micro avg) 0.8021
208
+ 2023-10-13 16:44:35,782 saving best model
209
+ 2023-10-13 16:44:36,372 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-13 16:44:43,685 epoch 10 - iter 147/1476 - loss 0.00753215 - time (sec): 7.31 - samples/sec: 2427.92 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-13 16:44:50,427 epoch 10 - iter 294/1476 - loss 0.00733874 - time (sec): 14.05 - samples/sec: 2397.65 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-13 16:44:57,073 epoch 10 - iter 441/1476 - loss 0.00807781 - time (sec): 20.70 - samples/sec: 2379.64 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-13 16:45:04,012 epoch 10 - iter 588/1476 - loss 0.00716263 - time (sec): 27.63 - samples/sec: 2380.05 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-13 16:45:10,975 epoch 10 - iter 735/1476 - loss 0.00686967 - time (sec): 34.60 - samples/sec: 2365.22 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-13 16:45:18,281 epoch 10 - iter 882/1476 - loss 0.00663991 - time (sec): 41.90 - samples/sec: 2403.12 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-13 16:45:24,959 epoch 10 - iter 1029/1476 - loss 0.00626594 - time (sec): 48.58 - samples/sec: 2376.51 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-13 16:45:32,198 epoch 10 - iter 1176/1476 - loss 0.00672382 - time (sec): 55.82 - samples/sec: 2373.49 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 16:45:39,249 epoch 10 - iter 1323/1476 - loss 0.00733306 - time (sec): 62.87 - samples/sec: 2376.93 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-13 16:45:46,111 epoch 10 - iter 1470/1476 - loss 0.00668996 - time (sec): 69.73 - samples/sec: 2378.72 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-13 16:45:46,370 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-13 16:45:46,370 EPOCH 10 done: loss 0.0067 - lr: 0.000000
222
+ 2023-10-13 16:45:57,519 DEV : loss 0.2591579258441925 - f1-score (micro avg) 0.8087
223
+ 2023-10-13 16:45:57,551 saving best model
224
+ 2023-10-13 16:45:58,550 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-13 16:45:58,552 Loading model from best epoch ...
226
+ 2023-10-13 16:46:00,002 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
227
+ 2023-10-13 16:46:05,936
228
+ Results:
229
+ - F-score (micro) 0.7887
230
+ - F-score (macro) 0.6932
231
+ - Accuracy 0.6774
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ loc 0.8380 0.8800 0.8584 858
237
+ pers 0.7456 0.7858 0.7652 537
238
+ org 0.5489 0.5530 0.5509 132
239
+ time 0.5373 0.6667 0.5950 54
240
+ prod 0.7647 0.6393 0.6964 61
241
+
242
+ micro avg 0.7712 0.8069 0.7887 1642
243
+ macro avg 0.6869 0.7050 0.6932 1642
244
+ weighted avg 0.7719 0.8069 0.7885 1642
245
+
246
+ 2023-10-13 16:46:05,936 ----------------------------------------------------------------------------------------------------