Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
57c2bca
•
1 Parent(s): b6d171b

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 +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db9d2e6f3c2f7e20c219cd3769ca4a7947294152bfc2a6a0c3b14c04b7c582c5
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 16:47:30 0.0000 0.5882 0.1539 0.6546 0.7360 0.6929 0.5643
3
+ 2 16:48:33 0.0000 0.1265 0.1280 0.6985 0.8001 0.7459 0.6220
4
+ 3 16:49:34 0.0000 0.0696 0.1284 0.7874 0.7955 0.7915 0.6839
5
+ 4 16:50:36 0.0000 0.0459 0.1347 0.7947 0.8316 0.8128 0.7107
6
+ 5 16:51:37 0.0000 0.0328 0.1764 0.8056 0.8425 0.8236 0.7282
7
+ 6 16:52:39 0.0000 0.0250 0.1854 0.7987 0.8362 0.8170 0.7196
8
+ 7 16:53:41 0.0000 0.0172 0.1876 0.8093 0.8408 0.8247 0.7300
9
+ 8 16:54:43 0.0000 0.0125 0.2045 0.8291 0.8391 0.8340 0.7406
10
+ 9 16:55:45 0.0000 0.0085 0.2095 0.8140 0.8419 0.8277 0.7328
11
+ 10 16:56:46 0.0000 0.0066 0.2124 0.8264 0.8454 0.8358 0.7425
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 16:46:35,065 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 16:46:35,066 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 16:46:35,066 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 16:46:35,066 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 16:46:35,066 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 16:46:35,067 Train: 5901 sentences
55
+ 2023-10-13 16:46:35,067 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 16:46:35,067 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 16:46:35,067 Training Params:
58
+ 2023-10-13 16:46:35,067 - learning_rate: "3e-05"
59
+ 2023-10-13 16:46:35,067 - mini_batch_size: "8"
60
+ 2023-10-13 16:46:35,067 - max_epochs: "10"
61
+ 2023-10-13 16:46:35,067 - shuffle: "True"
62
+ 2023-10-13 16:46:35,067 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 16:46:35,067 Plugins:
64
+ 2023-10-13 16:46:35,067 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 16:46:35,067 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 16:46:35,067 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 16:46:35,067 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 16:46:35,067 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 16:46:35,067 Computation:
70
+ 2023-10-13 16:46:35,067 - compute on device: cuda:0
71
+ 2023-10-13 16:46:35,067 - embedding storage: none
72
+ 2023-10-13 16:46:35,067 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 16:46:35,067 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
74
+ 2023-10-13 16:46:35,067 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 16:46:35,067 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 16:46:39,446 epoch 1 - iter 73/738 - loss 2.75876894 - time (sec): 4.38 - samples/sec: 3483.41 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 16:46:44,320 epoch 1 - iter 146/738 - loss 1.80884627 - time (sec): 9.25 - samples/sec: 3527.43 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 16:46:48,901 epoch 1 - iter 219/738 - loss 1.39634718 - time (sec): 13.83 - samples/sec: 3449.28 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 16:46:54,271 epoch 1 - iter 292/738 - loss 1.13609859 - time (sec): 19.20 - samples/sec: 3334.39 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 16:46:59,241 epoch 1 - iter 365/738 - loss 0.96487120 - time (sec): 24.17 - samples/sec: 3356.19 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 16:47:04,235 epoch 1 - iter 438/738 - loss 0.84886263 - time (sec): 29.17 - samples/sec: 3364.99 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 16:47:09,592 epoch 1 - iter 511/738 - loss 0.75569434 - time (sec): 34.52 - samples/sec: 3353.23 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 16:47:14,207 epoch 1 - iter 584/738 - loss 0.69445623 - time (sec): 39.14 - samples/sec: 3355.84 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 16:47:19,650 epoch 1 - iter 657/738 - loss 0.63336459 - time (sec): 44.58 - samples/sec: 3347.84 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 16:47:24,389 epoch 1 - iter 730/738 - loss 0.59174752 - time (sec): 49.32 - samples/sec: 3337.28 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 16:47:25,005 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 16:47:25,005 EPOCH 1 done: loss 0.5882 - lr: 0.000030
88
+ 2023-10-13 16:47:30,666 DEV : loss 0.15391376614570618 - f1-score (micro avg) 0.6929
89
+ 2023-10-13 16:47:30,695 saving best model
90
+ 2023-10-13 16:47:31,080 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 16:47:35,944 epoch 2 - iter 73/738 - loss 0.15186425 - time (sec): 4.86 - samples/sec: 3376.69 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 16:47:41,168 epoch 2 - iter 146/738 - loss 0.14890498 - time (sec): 10.09 - samples/sec: 3316.02 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 16:47:46,670 epoch 2 - iter 219/738 - loss 0.14354573 - time (sec): 15.59 - samples/sec: 3324.22 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 16:47:51,357 epoch 2 - iter 292/738 - loss 0.13792109 - time (sec): 20.28 - samples/sec: 3320.09 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 16:47:56,012 epoch 2 - iter 365/738 - loss 0.13912932 - time (sec): 24.93 - samples/sec: 3327.55 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 16:48:02,120 epoch 2 - iter 438/738 - loss 0.13583538 - time (sec): 31.04 - samples/sec: 3255.74 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 16:48:07,086 epoch 2 - iter 511/738 - loss 0.13334651 - time (sec): 36.00 - samples/sec: 3263.15 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 16:48:12,038 epoch 2 - iter 584/738 - loss 0.13084622 - time (sec): 40.96 - samples/sec: 3256.25 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 16:48:16,879 epoch 2 - iter 657/738 - loss 0.12811312 - time (sec): 45.80 - samples/sec: 3255.44 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 16:48:21,581 epoch 2 - iter 730/738 - loss 0.12603141 - time (sec): 50.50 - samples/sec: 3268.72 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 16:48:22,025 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 16:48:22,025 EPOCH 2 done: loss 0.1265 - lr: 0.000027
103
+ 2023-10-13 16:48:33,074 DEV : loss 0.12796831130981445 - f1-score (micro avg) 0.7459
104
+ 2023-10-13 16:48:33,102 saving best model
105
+ 2023-10-13 16:48:33,579 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 16:48:38,061 epoch 3 - iter 73/738 - loss 0.06383906 - time (sec): 4.48 - samples/sec: 3386.43 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 16:48:42,819 epoch 3 - iter 146/738 - loss 0.07115006 - time (sec): 9.24 - samples/sec: 3445.06 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 16:48:47,708 epoch 3 - iter 219/738 - loss 0.07055549 - time (sec): 14.13 - samples/sec: 3413.41 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 16:48:53,245 epoch 3 - iter 292/738 - loss 0.06676871 - time (sec): 19.66 - samples/sec: 3430.11 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 16:48:58,338 epoch 3 - iter 365/738 - loss 0.07018788 - time (sec): 24.76 - samples/sec: 3386.28 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 16:49:02,977 epoch 3 - iter 438/738 - loss 0.06934785 - time (sec): 29.40 - samples/sec: 3383.76 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 16:49:08,177 epoch 3 - iter 511/738 - loss 0.07101091 - time (sec): 34.60 - samples/sec: 3374.95 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 16:49:12,936 epoch 3 - iter 584/738 - loss 0.06876706 - time (sec): 39.36 - samples/sec: 3370.31 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 16:49:17,960 epoch 3 - iter 657/738 - loss 0.07113615 - time (sec): 44.38 - samples/sec: 3355.59 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 16:49:22,960 epoch 3 - iter 730/738 - loss 0.06952763 - time (sec): 49.38 - samples/sec: 3333.48 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 16:49:23,508 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 16:49:23,508 EPOCH 3 done: loss 0.0696 - lr: 0.000023
118
+ 2023-10-13 16:49:34,647 DEV : loss 0.12844610214233398 - f1-score (micro avg) 0.7915
119
+ 2023-10-13 16:49:34,675 saving best model
120
+ 2023-10-13 16:49:35,156 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 16:49:40,547 epoch 4 - iter 73/738 - loss 0.03685895 - time (sec): 5.39 - samples/sec: 3208.48 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 16:49:45,283 epoch 4 - iter 146/738 - loss 0.04110187 - time (sec): 10.12 - samples/sec: 3323.16 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 16:49:50,345 epoch 4 - iter 219/738 - loss 0.03920650 - time (sec): 15.19 - samples/sec: 3346.58 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 16:49:55,013 epoch 4 - iter 292/738 - loss 0.04046397 - time (sec): 19.85 - samples/sec: 3354.58 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 16:49:59,423 epoch 4 - iter 365/738 - loss 0.04108074 - time (sec): 24.26 - samples/sec: 3360.44 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 16:50:04,661 epoch 4 - iter 438/738 - loss 0.04132374 - time (sec): 29.50 - samples/sec: 3344.43 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 16:50:10,310 epoch 4 - iter 511/738 - loss 0.04572909 - time (sec): 35.15 - samples/sec: 3343.93 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 16:50:14,944 epoch 4 - iter 584/738 - loss 0.04580991 - time (sec): 39.79 - samples/sec: 3334.62 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 16:50:19,795 epoch 4 - iter 657/738 - loss 0.04521327 - time (sec): 44.64 - samples/sec: 3324.21 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 16:50:24,586 epoch 4 - iter 730/738 - loss 0.04616849 - time (sec): 49.43 - samples/sec: 3331.38 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 16:50:25,175 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 16:50:25,175 EPOCH 4 done: loss 0.0459 - lr: 0.000020
133
+ 2023-10-13 16:50:36,330 DEV : loss 0.1346866935491562 - f1-score (micro avg) 0.8128
134
+ 2023-10-13 16:50:36,360 saving best model
135
+ 2023-10-13 16:50:36,832 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 16:50:42,063 epoch 5 - iter 73/738 - loss 0.04944024 - time (sec): 5.23 - samples/sec: 3460.34 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 16:50:46,854 epoch 5 - iter 146/738 - loss 0.03832551 - time (sec): 10.02 - samples/sec: 3393.40 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 16:50:52,140 epoch 5 - iter 219/738 - loss 0.03785219 - time (sec): 15.31 - samples/sec: 3357.37 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 16:50:56,835 epoch 5 - iter 292/738 - loss 0.03537582 - time (sec): 20.00 - samples/sec: 3338.30 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 16:51:01,384 epoch 5 - iter 365/738 - loss 0.03443213 - time (sec): 24.55 - samples/sec: 3350.21 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 16:51:06,156 epoch 5 - iter 438/738 - loss 0.03236903 - time (sec): 29.32 - samples/sec: 3334.08 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 16:51:11,273 epoch 5 - iter 511/738 - loss 0.03406980 - time (sec): 34.44 - samples/sec: 3317.60 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 16:51:16,186 epoch 5 - iter 584/738 - loss 0.03283544 - time (sec): 39.35 - samples/sec: 3303.95 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 16:51:20,707 epoch 5 - iter 657/738 - loss 0.03218738 - time (sec): 43.87 - samples/sec: 3316.58 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 16:51:26,258 epoch 5 - iter 730/738 - loss 0.03237876 - time (sec): 49.42 - samples/sec: 3331.87 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 16:51:26,764 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 16:51:26,764 EPOCH 5 done: loss 0.0328 - lr: 0.000017
148
+ 2023-10-13 16:51:37,913 DEV : loss 0.1763695776462555 - f1-score (micro avg) 0.8236
149
+ 2023-10-13 16:51:37,942 saving best model
150
+ 2023-10-13 16:51:38,405 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 16:51:43,720 epoch 6 - iter 73/738 - loss 0.02851833 - time (sec): 5.31 - samples/sec: 3401.46 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 16:51:48,974 epoch 6 - iter 146/738 - loss 0.02463249 - time (sec): 10.56 - samples/sec: 3353.65 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 16:51:54,352 epoch 6 - iter 219/738 - loss 0.02827618 - time (sec): 15.94 - samples/sec: 3371.69 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-13 16:51:59,040 epoch 6 - iter 292/738 - loss 0.02592426 - time (sec): 20.63 - samples/sec: 3378.60 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 16:52:03,788 epoch 6 - iter 365/738 - loss 0.02549278 - time (sec): 25.38 - samples/sec: 3375.93 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 16:52:08,850 epoch 6 - iter 438/738 - loss 0.02522983 - time (sec): 30.44 - samples/sec: 3350.26 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-13 16:52:13,892 epoch 6 - iter 511/738 - loss 0.02559890 - time (sec): 35.48 - samples/sec: 3332.52 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 16:52:18,464 epoch 6 - iter 584/738 - loss 0.02545238 - time (sec): 40.05 - samples/sec: 3328.41 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 16:52:23,093 epoch 6 - iter 657/738 - loss 0.02493318 - time (sec): 44.68 - samples/sec: 3329.62 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-13 16:52:27,661 epoch 6 - iter 730/738 - loss 0.02518905 - time (sec): 49.25 - samples/sec: 3339.91 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-13 16:52:28,128 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 16:52:28,128 EPOCH 6 done: loss 0.0250 - lr: 0.000013
163
+ 2023-10-13 16:52:39,285 DEV : loss 0.18539553880691528 - f1-score (micro avg) 0.817
164
+ 2023-10-13 16:52:39,315 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 16:52:43,755 epoch 7 - iter 73/738 - loss 0.01011457 - time (sec): 4.44 - samples/sec: 3463.78 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 16:52:49,698 epoch 7 - iter 146/738 - loss 0.00991157 - time (sec): 10.38 - samples/sec: 3179.21 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 16:52:54,136 epoch 7 - iter 219/738 - loss 0.01639992 - time (sec): 14.82 - samples/sec: 3225.00 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 16:52:59,643 epoch 7 - iter 292/738 - loss 0.01771782 - time (sec): 20.33 - samples/sec: 3207.13 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 16:53:04,291 epoch 7 - iter 365/738 - loss 0.01626466 - time (sec): 24.98 - samples/sec: 3231.89 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 16:53:08,896 epoch 7 - iter 438/738 - loss 0.01633743 - time (sec): 29.58 - samples/sec: 3240.55 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 16:53:15,008 epoch 7 - iter 511/738 - loss 0.01619167 - time (sec): 35.69 - samples/sec: 3240.35 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 16:53:20,345 epoch 7 - iter 584/738 - loss 0.01642316 - time (sec): 41.03 - samples/sec: 3238.07 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 16:53:25,482 epoch 7 - iter 657/738 - loss 0.01739578 - time (sec): 46.17 - samples/sec: 3236.69 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 16:53:30,254 epoch 7 - iter 730/738 - loss 0.01737564 - time (sec): 50.94 - samples/sec: 3238.00 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 16:53:30,720 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 16:53:30,720 EPOCH 7 done: loss 0.0172 - lr: 0.000010
177
+ 2023-10-13 16:53:41,882 DEV : loss 0.18756036460399628 - f1-score (micro avg) 0.8247
178
+ 2023-10-13 16:53:41,911 saving best model
179
+ 2023-10-13 16:53:42,390 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 16:53:47,374 epoch 8 - iter 73/738 - loss 0.00892796 - time (sec): 4.98 - samples/sec: 3368.70 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-13 16:53:52,625 epoch 8 - iter 146/738 - loss 0.01253336 - time (sec): 10.23 - samples/sec: 3345.02 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 16:53:57,957 epoch 8 - iter 219/738 - loss 0.01654324 - time (sec): 15.57 - samples/sec: 3364.89 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 16:54:03,288 epoch 8 - iter 292/738 - loss 0.01734773 - time (sec): 20.90 - samples/sec: 3307.99 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-13 16:54:08,395 epoch 8 - iter 365/738 - loss 0.01551208 - time (sec): 26.00 - samples/sec: 3285.30 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 16:54:13,444 epoch 8 - iter 438/738 - loss 0.01347784 - time (sec): 31.05 - samples/sec: 3297.82 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 16:54:18,073 epoch 8 - iter 511/738 - loss 0.01260285 - time (sec): 35.68 - samples/sec: 3310.59 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-13 16:54:22,616 epoch 8 - iter 584/738 - loss 0.01238670 - time (sec): 40.22 - samples/sec: 3297.36 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 16:54:27,063 epoch 8 - iter 657/738 - loss 0.01286577 - time (sec): 44.67 - samples/sec: 3312.04 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 16:54:31,953 epoch 8 - iter 730/738 - loss 0.01257961 - time (sec): 49.56 - samples/sec: 3315.55 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-13 16:54:32,610 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 16:54:32,610 EPOCH 8 done: loss 0.0125 - lr: 0.000007
192
+ 2023-10-13 16:54:43,760 DEV : loss 0.20449210703372955 - f1-score (micro avg) 0.834
193
+ 2023-10-13 16:54:43,789 saving best model
194
+ 2023-10-13 16:54:44,362 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-13 16:54:49,824 epoch 9 - iter 73/738 - loss 0.01064858 - time (sec): 5.46 - samples/sec: 3272.76 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 16:54:54,742 epoch 9 - iter 146/738 - loss 0.00779519 - time (sec): 10.37 - samples/sec: 3357.34 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 16:54:59,363 epoch 9 - iter 219/738 - loss 0.00658462 - time (sec): 15.00 - samples/sec: 3353.64 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-13 16:55:04,212 epoch 9 - iter 292/738 - loss 0.00639633 - time (sec): 19.84 - samples/sec: 3360.35 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 16:55:08,608 epoch 9 - iter 365/738 - loss 0.00784894 - time (sec): 24.24 - samples/sec: 3350.02 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 16:55:13,771 epoch 9 - iter 438/738 - loss 0.00753028 - time (sec): 29.40 - samples/sec: 3336.58 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-13 16:55:18,929 epoch 9 - iter 511/738 - loss 0.00848044 - time (sec): 34.56 - samples/sec: 3352.91 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 16:55:23,474 epoch 9 - iter 584/738 - loss 0.00849055 - time (sec): 39.11 - samples/sec: 3376.49 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 16:55:28,220 epoch 9 - iter 657/738 - loss 0.00861082 - time (sec): 43.85 - samples/sec: 3381.01 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-13 16:55:33,280 epoch 9 - iter 730/738 - loss 0.00844713 - time (sec): 48.91 - samples/sec: 3364.31 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-13 16:55:33,870 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 16:55:33,870 EPOCH 9 done: loss 0.0085 - lr: 0.000003
207
+ 2023-10-13 16:55:45,043 DEV : loss 0.20950576663017273 - f1-score (micro avg) 0.8277
208
+ 2023-10-13 16:55:45,073 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 16:55:50,272 epoch 10 - iter 73/738 - loss 0.00495315 - time (sec): 5.20 - samples/sec: 3446.07 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 16:55:54,764 epoch 10 - iter 146/738 - loss 0.00461775 - time (sec): 9.69 - samples/sec: 3396.23 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 16:55:59,868 epoch 10 - iter 219/738 - loss 0.00379146 - time (sec): 14.79 - samples/sec: 3375.10 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 16:56:04,753 epoch 10 - iter 292/738 - loss 0.00373819 - time (sec): 19.68 - samples/sec: 3317.15 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 16:56:10,064 epoch 10 - iter 365/738 - loss 0.00620564 - time (sec): 24.99 - samples/sec: 3360.08 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 16:56:14,865 epoch 10 - iter 438/738 - loss 0.00579438 - time (sec): 29.79 - samples/sec: 3358.73 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 16:56:19,725 epoch 10 - iter 511/738 - loss 0.00610258 - time (sec): 34.65 - samples/sec: 3364.26 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 16:56:24,577 epoch 10 - iter 584/738 - loss 0.00640510 - time (sec): 39.50 - samples/sec: 3374.56 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 16:56:29,147 epoch 10 - iter 657/738 - loss 0.00631027 - time (sec): 44.07 - samples/sec: 3382.29 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 16:56:34,418 epoch 10 - iter 730/738 - loss 0.00658051 - time (sec): 49.34 - samples/sec: 3345.91 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 16:56:34,856 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 16:56:34,856 EPOCH 10 done: loss 0.0066 - lr: 0.000000
221
+ 2023-10-13 16:56:46,029 DEV : loss 0.2123527079820633 - f1-score (micro avg) 0.8358
222
+ 2023-10-13 16:56:46,058 saving best model
223
+ 2023-10-13 16:56:46,995 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-13 16:56:46,997 Loading model from best epoch ...
225
+ 2023-10-13 16:56:48,450 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
226
+ 2023-10-13 16:56:54,898
227
+ Results:
228
+ - F-score (micro) 0.7941
229
+ - F-score (macro) 0.6902
230
+ - Accuracy 0.6827
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.8571 0.8741 0.8656 858
236
+ pers 0.7535 0.8026 0.7773 537
237
+ org 0.5405 0.6061 0.5714 132
238
+ time 0.4783 0.6111 0.5366 54
239
+ prod 0.7119 0.6885 0.7000 61
240
+
241
+ micro avg 0.7754 0.8136 0.7941 1642
242
+ macro avg 0.6683 0.7165 0.6902 1642
243
+ weighted avg 0.7799 0.8136 0.7961 1642
244
+
245
+ 2023-10-13 16:56:54,898 ----------------------------------------------------------------------------------------------------