Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
11e83cf
•
1 Parent(s): af36462

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697581744.bce904bcef33.2482.13 +3 -0
  5. test.tsv +0 -0
  6. training.log +242 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43da13df8cfd06fcb195516cfee1555b67087f3eac5b2350ae10473ad789da1c
3
+ size 440966725
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 22:30:00 0.0000 0.5810 0.1130 0.7306 0.7892 0.7588 0.6397
3
+ 2 22:31:04 0.0000 0.1202 0.1062 0.7871 0.7961 0.7916 0.6804
4
+ 3 22:32:07 0.0000 0.0693 0.1311 0.8136 0.8351 0.8242 0.7218
5
+ 4 22:33:11 0.0000 0.0499 0.1413 0.8100 0.8202 0.8150 0.7128
6
+ 5 22:34:15 0.0000 0.0347 0.1900 0.8390 0.8236 0.8312 0.7329
7
+ 6 22:35:19 0.0000 0.0236 0.2037 0.8220 0.8436 0.8327 0.7398
8
+ 7 22:36:23 0.0000 0.0167 0.2062 0.8274 0.8345 0.8309 0.7370
9
+ 8 22:37:25 0.0000 0.0116 0.2062 0.8339 0.8425 0.8382 0.7433
10
+ 9 22:38:29 0.0000 0.0068 0.2081 0.8397 0.8551 0.8473 0.7590
11
+ 10 22:39:32 0.0000 0.0047 0.2178 0.8383 0.8494 0.8438 0.7524
runs/events.out.tfevents.1697581744.bce904bcef33.2482.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:677fa98a06045ecb137a4c8603e6e33edea23a21b1789243fc45fe48723ae015
3
+ size 415388
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 22:29:04,133 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 22:29:04,134 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
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): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
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): ElectraSelfOutput(
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): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
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
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=21, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 22:29:04,134 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 22:29:04,135 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
48
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
49
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 22:29:04,135 Train: 5901 sentences
51
+ 2023-10-17 22:29:04,135 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 22:29:04,135 Training Params:
54
+ 2023-10-17 22:29:04,135 - learning_rate: "5e-05"
55
+ 2023-10-17 22:29:04,135 - mini_batch_size: "8"
56
+ 2023-10-17 22:29:04,135 - max_epochs: "10"
57
+ 2023-10-17 22:29:04,135 - shuffle: "True"
58
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 22:29:04,135 Plugins:
60
+ 2023-10-17 22:29:04,135 - TensorboardLogger
61
+ 2023-10-17 22:29:04,135 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 22:29:04,135 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 22:29:04,135 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 22:29:04,135 Computation:
67
+ 2023-10-17 22:29:04,135 - compute on device: cuda:0
68
+ 2023-10-17 22:29:04,135 - embedding storage: none
69
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 22:29:04,135 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
71
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 22:29:04,135 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 22:29:04,135 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 22:29:09,478 epoch 1 - iter 73/738 - loss 2.99837415 - time (sec): 5.34 - samples/sec: 3166.80 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 22:29:13,992 epoch 1 - iter 146/738 - loss 1.93510546 - time (sec): 9.86 - samples/sec: 3213.05 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 22:29:18,605 epoch 1 - iter 219/738 - loss 1.45592106 - time (sec): 14.47 - samples/sec: 3237.90 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 22:29:23,729 epoch 1 - iter 292/738 - loss 1.16902073 - time (sec): 19.59 - samples/sec: 3260.44 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 22:29:29,137 epoch 1 - iter 365/738 - loss 0.97478204 - time (sec): 25.00 - samples/sec: 3288.96 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 22:29:34,394 epoch 1 - iter 438/738 - loss 0.85064874 - time (sec): 30.26 - samples/sec: 3282.58 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 22:29:38,954 epoch 1 - iter 511/738 - loss 0.76809817 - time (sec): 34.82 - samples/sec: 3284.37 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 22:29:43,774 epoch 1 - iter 584/738 - loss 0.69380777 - time (sec): 39.64 - samples/sec: 3297.78 - lr: 0.000039 - momentum: 0.000000
82
+ 2023-10-17 22:29:48,885 epoch 1 - iter 657/738 - loss 0.63363005 - time (sec): 44.75 - samples/sec: 3296.16 - lr: 0.000044 - momentum: 0.000000
83
+ 2023-10-17 22:29:53,841 epoch 1 - iter 730/738 - loss 0.58383020 - time (sec): 49.70 - samples/sec: 3320.47 - lr: 0.000049 - momentum: 0.000000
84
+ 2023-10-17 22:29:54,280 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 22:29:54,280 EPOCH 1 done: loss 0.5810 - lr: 0.000049
86
+ 2023-10-17 22:30:00,666 DEV : loss 0.11302945762872696 - f1-score (micro avg) 0.7588
87
+ 2023-10-17 22:30:00,696 saving best model
88
+ 2023-10-17 22:30:01,082 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 22:30:06,731 epoch 2 - iter 73/738 - loss 0.13556365 - time (sec): 5.65 - samples/sec: 3264.65 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 22:30:11,564 epoch 2 - iter 146/738 - loss 0.12924036 - time (sec): 10.48 - samples/sec: 3272.73 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 22:30:16,659 epoch 2 - iter 219/738 - loss 0.12904174 - time (sec): 15.58 - samples/sec: 3216.43 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 22:30:21,829 epoch 2 - iter 292/738 - loss 0.12726226 - time (sec): 20.75 - samples/sec: 3213.20 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 22:30:26,397 epoch 2 - iter 365/738 - loss 0.12773492 - time (sec): 25.31 - samples/sec: 3210.16 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 22:30:31,342 epoch 2 - iter 438/738 - loss 0.12584037 - time (sec): 30.26 - samples/sec: 3214.18 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 22:30:35,893 epoch 2 - iter 511/738 - loss 0.12575633 - time (sec): 34.81 - samples/sec: 3231.66 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 22:30:40,717 epoch 2 - iter 584/738 - loss 0.12360271 - time (sec): 39.63 - samples/sec: 3238.30 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 22:30:45,964 epoch 2 - iter 657/738 - loss 0.12251002 - time (sec): 44.88 - samples/sec: 3232.19 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 22:30:51,263 epoch 2 - iter 730/738 - loss 0.12156812 - time (sec): 50.18 - samples/sec: 3246.27 - lr: 0.000045 - momentum: 0.000000
99
+ 2023-10-17 22:30:52,229 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 22:30:52,230 EPOCH 2 done: loss 0.1202 - lr: 0.000045
101
+ 2023-10-17 22:31:04,398 DEV : loss 0.10620676726102829 - f1-score (micro avg) 0.7916
102
+ 2023-10-17 22:31:04,432 saving best model
103
+ 2023-10-17 22:31:04,975 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 22:31:10,816 epoch 3 - iter 73/738 - loss 0.07909692 - time (sec): 5.83 - samples/sec: 3171.41 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 22:31:15,736 epoch 3 - iter 146/738 - loss 0.07174765 - time (sec): 10.76 - samples/sec: 3220.31 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 22:31:20,225 epoch 3 - iter 219/738 - loss 0.07516061 - time (sec): 15.24 - samples/sec: 3229.49 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 22:31:25,006 epoch 3 - iter 292/738 - loss 0.07592855 - time (sec): 20.02 - samples/sec: 3258.50 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 22:31:29,791 epoch 3 - iter 365/738 - loss 0.07330696 - time (sec): 24.81 - samples/sec: 3265.19 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 22:31:35,103 epoch 3 - iter 438/738 - loss 0.07170697 - time (sec): 30.12 - samples/sec: 3259.41 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 22:31:40,196 epoch 3 - iter 511/738 - loss 0.07160535 - time (sec): 35.21 - samples/sec: 3281.25 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 22:31:44,916 epoch 3 - iter 584/738 - loss 0.07165988 - time (sec): 39.93 - samples/sec: 3271.92 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 22:31:50,041 epoch 3 - iter 657/738 - loss 0.07097376 - time (sec): 45.06 - samples/sec: 3262.94 - lr: 0.000040 - momentum: 0.000000
113
+ 2023-10-17 22:31:55,409 epoch 3 - iter 730/738 - loss 0.06940338 - time (sec): 50.43 - samples/sec: 3262.11 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 22:31:55,939 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 22:31:55,939 EPOCH 3 done: loss 0.0693 - lr: 0.000039
116
+ 2023-10-17 22:32:07,887 DEV : loss 0.13108941912651062 - f1-score (micro avg) 0.8242
117
+ 2023-10-17 22:32:07,925 saving best model
118
+ 2023-10-17 22:32:08,507 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 22:32:13,135 epoch 4 - iter 73/738 - loss 0.03703471 - time (sec): 4.63 - samples/sec: 3340.02 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 22:32:18,045 epoch 4 - iter 146/738 - loss 0.04150633 - time (sec): 9.54 - samples/sec: 3270.43 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 22:32:23,041 epoch 4 - iter 219/738 - loss 0.04123992 - time (sec): 14.53 - samples/sec: 3241.31 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 22:32:29,054 epoch 4 - iter 292/738 - loss 0.04410608 - time (sec): 20.54 - samples/sec: 3232.21 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 22:32:34,235 epoch 4 - iter 365/738 - loss 0.04659042 - time (sec): 25.73 - samples/sec: 3244.52 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 22:32:38,717 epoch 4 - iter 438/738 - loss 0.04619151 - time (sec): 30.21 - samples/sec: 3250.55 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 22:32:43,578 epoch 4 - iter 511/738 - loss 0.04635101 - time (sec): 35.07 - samples/sec: 3264.21 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 22:32:48,576 epoch 4 - iter 584/738 - loss 0.04536034 - time (sec): 40.07 - samples/sec: 3252.74 - lr: 0.000035 - momentum: 0.000000
127
+ 2023-10-17 22:32:53,408 epoch 4 - iter 657/738 - loss 0.04699631 - time (sec): 44.90 - samples/sec: 3255.70 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 22:32:59,545 epoch 4 - iter 730/738 - loss 0.04985825 - time (sec): 51.04 - samples/sec: 3227.83 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 22:33:00,140 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 22:33:00,141 EPOCH 4 done: loss 0.0499 - lr: 0.000033
131
+ 2023-10-17 22:33:11,846 DEV : loss 0.14125068485736847 - f1-score (micro avg) 0.815
132
+ 2023-10-17 22:33:11,880 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 22:33:16,573 epoch 5 - iter 73/738 - loss 0.02879190 - time (sec): 4.69 - samples/sec: 3375.41 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 22:33:21,534 epoch 5 - iter 146/738 - loss 0.03371840 - time (sec): 9.65 - samples/sec: 3230.98 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 22:33:26,804 epoch 5 - iter 219/738 - loss 0.02945090 - time (sec): 14.92 - samples/sec: 3219.82 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 22:33:32,072 epoch 5 - iter 292/738 - loss 0.03027760 - time (sec): 20.19 - samples/sec: 3232.69 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 22:33:37,069 epoch 5 - iter 365/738 - loss 0.03506228 - time (sec): 25.19 - samples/sec: 3268.76 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 22:33:42,047 epoch 5 - iter 438/738 - loss 0.03543225 - time (sec): 30.17 - samples/sec: 3282.24 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 22:33:46,992 epoch 5 - iter 511/738 - loss 0.03479354 - time (sec): 35.11 - samples/sec: 3270.66 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 22:33:52,994 epoch 5 - iter 584/738 - loss 0.03639606 - time (sec): 41.11 - samples/sec: 3261.04 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 22:33:57,710 epoch 5 - iter 657/738 - loss 0.03555295 - time (sec): 45.83 - samples/sec: 3261.10 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 22:34:02,438 epoch 5 - iter 730/738 - loss 0.03486226 - time (sec): 50.56 - samples/sec: 3265.54 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 22:34:02,901 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 22:34:02,901 EPOCH 5 done: loss 0.0347 - lr: 0.000028
145
+ 2023-10-17 22:34:15,042 DEV : loss 0.19004222750663757 - f1-score (micro avg) 0.8312
146
+ 2023-10-17 22:34:15,088 saving best model
147
+ 2023-10-17 22:34:15,573 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 22:34:20,441 epoch 6 - iter 73/738 - loss 0.02813745 - time (sec): 4.86 - samples/sec: 3296.59 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 22:34:25,602 epoch 6 - iter 146/738 - loss 0.02518261 - time (sec): 10.03 - samples/sec: 3225.85 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 22:34:31,064 epoch 6 - iter 219/738 - loss 0.02167308 - time (sec): 15.49 - samples/sec: 3216.28 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 22:34:35,610 epoch 6 - iter 292/738 - loss 0.02310727 - time (sec): 20.03 - samples/sec: 3242.49 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 22:34:40,377 epoch 6 - iter 365/738 - loss 0.02350712 - time (sec): 24.80 - samples/sec: 3262.02 - lr: 0.000025 - momentum: 0.000000
153
+ 2023-10-17 22:34:45,894 epoch 6 - iter 438/738 - loss 0.02568561 - time (sec): 30.32 - samples/sec: 3251.89 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 22:34:50,637 epoch 6 - iter 511/738 - loss 0.02533559 - time (sec): 35.06 - samples/sec: 3248.03 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 22:34:55,852 epoch 6 - iter 584/738 - loss 0.02483365 - time (sec): 40.28 - samples/sec: 3242.98 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 22:35:01,847 epoch 6 - iter 657/738 - loss 0.02444670 - time (sec): 46.27 - samples/sec: 3218.62 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 22:35:06,861 epoch 6 - iter 730/738 - loss 0.02362799 - time (sec): 51.28 - samples/sec: 3215.12 - lr: 0.000022 - momentum: 0.000000
158
+ 2023-10-17 22:35:07,312 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 22:35:07,313 EPOCH 6 done: loss 0.0236 - lr: 0.000022
160
+ 2023-10-17 22:35:19,340 DEV : loss 0.20369166135787964 - f1-score (micro avg) 0.8327
161
+ 2023-10-17 22:35:19,377 saving best model
162
+ 2023-10-17 22:35:19,893 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-17 22:35:25,515 epoch 7 - iter 73/738 - loss 0.01350406 - time (sec): 5.62 - samples/sec: 3361.02 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-17 22:35:30,665 epoch 7 - iter 146/738 - loss 0.01445533 - time (sec): 10.77 - samples/sec: 3283.82 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 22:35:35,388 epoch 7 - iter 219/738 - loss 0.01349065 - time (sec): 15.49 - samples/sec: 3296.44 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 22:35:40,791 epoch 7 - iter 292/738 - loss 0.01184519 - time (sec): 20.90 - samples/sec: 3258.88 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-17 22:35:45,268 epoch 7 - iter 365/738 - loss 0.01302031 - time (sec): 25.37 - samples/sec: 3278.92 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-17 22:35:50,359 epoch 7 - iter 438/738 - loss 0.01425148 - time (sec): 30.46 - samples/sec: 3268.83 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 22:35:55,534 epoch 7 - iter 511/738 - loss 0.01540854 - time (sec): 35.64 - samples/sec: 3248.78 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 22:36:00,485 epoch 7 - iter 584/738 - loss 0.01593386 - time (sec): 40.59 - samples/sec: 3255.73 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 22:36:05,813 epoch 7 - iter 657/738 - loss 0.01714758 - time (sec): 45.92 - samples/sec: 3233.90 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 22:36:11,021 epoch 7 - iter 730/738 - loss 0.01677898 - time (sec): 51.13 - samples/sec: 3219.64 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 22:36:11,589 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-17 22:36:11,590 EPOCH 7 done: loss 0.0167 - lr: 0.000017
175
+ 2023-10-17 22:36:23,302 DEV : loss 0.20619168877601624 - f1-score (micro avg) 0.8309
176
+ 2023-10-17 22:36:23,335 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 22:36:28,762 epoch 8 - iter 73/738 - loss 0.01436214 - time (sec): 5.43 - samples/sec: 3505.01 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 22:36:33,706 epoch 8 - iter 146/738 - loss 0.01406720 - time (sec): 10.37 - samples/sec: 3337.79 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 22:36:39,250 epoch 8 - iter 219/738 - loss 0.01357334 - time (sec): 15.91 - samples/sec: 3295.54 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-17 22:36:44,612 epoch 8 - iter 292/738 - loss 0.01362606 - time (sec): 21.28 - samples/sec: 3277.39 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-17 22:36:49,362 epoch 8 - iter 365/738 - loss 0.01258376 - time (sec): 26.03 - samples/sec: 3288.03 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 22:36:54,351 epoch 8 - iter 438/738 - loss 0.01195634 - time (sec): 31.01 - samples/sec: 3256.51 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 22:36:59,301 epoch 8 - iter 511/738 - loss 0.01131119 - time (sec): 35.97 - samples/sec: 3247.35 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 22:37:04,249 epoch 8 - iter 584/738 - loss 0.01151810 - time (sec): 40.91 - samples/sec: 3262.34 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 22:37:09,202 epoch 8 - iter 657/738 - loss 0.01136472 - time (sec): 45.87 - samples/sec: 3258.75 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 22:37:13,756 epoch 8 - iter 730/738 - loss 0.01129012 - time (sec): 50.42 - samples/sec: 3264.76 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-17 22:37:14,310 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 22:37:14,310 EPOCH 8 done: loss 0.0116 - lr: 0.000011
189
+ 2023-10-17 22:37:25,955 DEV : loss 0.20618367195129395 - f1-score (micro avg) 0.8382
190
+ 2023-10-17 22:37:25,994 saving best model
191
+ 2023-10-17 22:37:26,535 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-17 22:37:31,040 epoch 9 - iter 73/738 - loss 0.00179149 - time (sec): 4.50 - samples/sec: 3318.58 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-17 22:37:35,954 epoch 9 - iter 146/738 - loss 0.00388670 - time (sec): 9.42 - samples/sec: 3296.02 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-17 22:37:42,573 epoch 9 - iter 219/738 - loss 0.00558100 - time (sec): 16.04 - samples/sec: 3216.48 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-17 22:37:46,905 epoch 9 - iter 292/738 - loss 0.00579759 - time (sec): 20.37 - samples/sec: 3248.07 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 22:37:51,672 epoch 9 - iter 365/738 - loss 0.00592703 - time (sec): 25.14 - samples/sec: 3250.17 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 22:37:57,350 epoch 9 - iter 438/738 - loss 0.00668828 - time (sec): 30.81 - samples/sec: 3240.67 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 22:38:02,024 epoch 9 - iter 511/738 - loss 0.00651091 - time (sec): 35.49 - samples/sec: 3235.47 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 22:38:07,184 epoch 9 - iter 584/738 - loss 0.00667925 - time (sec): 40.65 - samples/sec: 3233.36 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 22:38:12,714 epoch 9 - iter 657/738 - loss 0.00716367 - time (sec): 46.18 - samples/sec: 3221.77 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 22:38:17,563 epoch 9 - iter 730/738 - loss 0.00684617 - time (sec): 51.03 - samples/sec: 3226.78 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 22:38:18,091 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 22:38:18,091 EPOCH 9 done: loss 0.0068 - lr: 0.000006
204
+ 2023-10-17 22:38:29,523 DEV : loss 0.20809388160705566 - f1-score (micro avg) 0.8473
205
+ 2023-10-17 22:38:29,554 saving best model
206
+ 2023-10-17 22:38:30,106 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 22:38:34,557 epoch 10 - iter 73/738 - loss 0.00157154 - time (sec): 4.45 - samples/sec: 3307.08 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-17 22:38:39,511 epoch 10 - iter 146/738 - loss 0.00473884 - time (sec): 9.40 - samples/sec: 3262.89 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-17 22:38:44,413 epoch 10 - iter 219/738 - loss 0.00435182 - time (sec): 14.30 - samples/sec: 3245.94 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-17 22:38:50,176 epoch 10 - iter 292/738 - loss 0.00461898 - time (sec): 20.06 - samples/sec: 3265.73 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 22:38:54,905 epoch 10 - iter 365/738 - loss 0.00437464 - time (sec): 24.79 - samples/sec: 3267.62 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 22:39:00,079 epoch 10 - iter 438/738 - loss 0.00585767 - time (sec): 29.97 - samples/sec: 3265.78 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 22:39:04,813 epoch 10 - iter 511/738 - loss 0.00504414 - time (sec): 34.70 - samples/sec: 3278.60 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 22:39:09,643 epoch 10 - iter 584/738 - loss 0.00486786 - time (sec): 39.53 - samples/sec: 3281.88 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 22:39:15,461 epoch 10 - iter 657/738 - loss 0.00498413 - time (sec): 45.35 - samples/sec: 3278.45 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 22:39:20,217 epoch 10 - iter 730/738 - loss 0.00471586 - time (sec): 50.11 - samples/sec: 3274.82 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 22:39:20,859 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 22:39:20,859 EPOCH 10 done: loss 0.0047 - lr: 0.000000
219
+ 2023-10-17 22:39:32,442 DEV : loss 0.21777039766311646 - f1-score (micro avg) 0.8438
220
+ 2023-10-17 22:39:32,871 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-17 22:39:32,873 Loading model from best epoch ...
222
+ 2023-10-17 22:39:34,269 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
223
+ 2023-10-17 22:39:40,451
224
+ Results:
225
+ - F-score (micro) 0.8122
226
+ - F-score (macro) 0.7141
227
+ - Accuracy 0.7007
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.8672 0.8904 0.8787 858
233
+ pers 0.7737 0.8212 0.7967 537
234
+ org 0.5714 0.6364 0.6022 132
235
+ prod 0.6667 0.6885 0.6774 61
236
+ time 0.5714 0.6667 0.6154 54
237
+
238
+ micro avg 0.7929 0.8325 0.8122 1642
239
+ macro avg 0.6901 0.7406 0.7141 1642
240
+ weighted avg 0.7957 0.8325 0.8135 1642
241
+
242
+ 2023-10-17 22:39:40,451 ----------------------------------------------------------------------------------------------------