Upload folder using huggingface_hub
Browse files- best-model.pt +3 -0
- dev.tsv +0 -0
- final-model.pt +3 -0
- loss.tsv +11 -0
- runs/events.out.tfevents.1697159463.de2e83fddbee.1952.11 +3 -0
- test.tsv +0 -0
- training.log +262 -0
best-model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2c1f65be5109f053d4cbf4b35ff973193dd9d5ad59a522c6c2327fc4757f25e
|
3 |
+
size 870793839
|
dev.tsv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
final-model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c7f93b204d57440841ab10e8490d51d13b84cb5f38bc62a4c7c4723dff38089
|
3 |
+
size 870793956
|
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 01:20:33 0.0002 0.8182 0.1346 0.6681 0.6968 0.6822 0.5427
|
3 |
+
2 01:30:00 0.0001 0.1191 0.0906 0.7220 0.7726 0.7464 0.6192
|
4 |
+
3 01:39:39 0.0001 0.0738 0.1063 0.7385 0.7477 0.7431 0.6189
|
5 |
+
4 01:49:13 0.0001 0.0547 0.1299 0.7331 0.7952 0.7629 0.6374
|
6 |
+
5 01:58:31 0.0001 0.0403 0.1589 0.7333 0.7839 0.7578 0.6323
|
7 |
+
6 02:07:43 0.0001 0.0296 0.1692 0.7360 0.7885 0.7613 0.6377
|
8 |
+
7 02:16:54 0.0001 0.0217 0.1954 0.7331 0.7862 0.7587 0.6318
|
9 |
+
8 02:26:07 0.0000 0.0159 0.2072 0.7453 0.7681 0.7565 0.6299
|
10 |
+
9 02:35:21 0.0000 0.0103 0.2197 0.7447 0.7919 0.7675 0.6440
|
11 |
+
10 02:44:38 0.0000 0.0076 0.2271 0.7484 0.7907 0.7690 0.6454
|
runs/events.out.tfevents.1697159463.de2e83fddbee.1952.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612614df13af860845073cf243b0233f0ee4433921bc9074094fc0cd734c5c32
|
3 |
+
size 1108164
|
test.tsv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training.log
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2023-10-13 01:11:03,794 ----------------------------------------------------------------------------------------------------
|
2 |
+
2023-10-13 01:11:03,796 Model: "SequenceTagger(
|
3 |
+
(embeddings): ByT5Embeddings(
|
4 |
+
(model): T5EncoderModel(
|
5 |
+
(shared): Embedding(384, 1472)
|
6 |
+
(encoder): T5Stack(
|
7 |
+
(embed_tokens): Embedding(384, 1472)
|
8 |
+
(block): ModuleList(
|
9 |
+
(0): T5Block(
|
10 |
+
(layer): ModuleList(
|
11 |
+
(0): T5LayerSelfAttention(
|
12 |
+
(SelfAttention): T5Attention(
|
13 |
+
(q): Linear(in_features=1472, out_features=384, bias=False)
|
14 |
+
(k): Linear(in_features=1472, out_features=384, bias=False)
|
15 |
+
(v): Linear(in_features=1472, out_features=384, bias=False)
|
16 |
+
(o): Linear(in_features=384, out_features=1472, bias=False)
|
17 |
+
(relative_attention_bias): Embedding(32, 6)
|
18 |
+
)
|
19 |
+
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
|
20 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
21 |
+
)
|
22 |
+
(1): T5LayerFF(
|
23 |
+
(DenseReluDense): T5DenseGatedActDense(
|
24 |
+
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
|
25 |
+
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
|
26 |
+
(wo): Linear(in_features=3584, out_features=1472, bias=False)
|
27 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
28 |
+
(act): NewGELUActivation()
|
29 |
+
)
|
30 |
+
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
|
31 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
32 |
+
)
|
33 |
+
)
|
34 |
+
)
|
35 |
+
(1-11): 11 x T5Block(
|
36 |
+
(layer): ModuleList(
|
37 |
+
(0): T5LayerSelfAttention(
|
38 |
+
(SelfAttention): T5Attention(
|
39 |
+
(q): Linear(in_features=1472, out_features=384, bias=False)
|
40 |
+
(k): Linear(in_features=1472, out_features=384, bias=False)
|
41 |
+
(v): Linear(in_features=1472, out_features=384, bias=False)
|
42 |
+
(o): Linear(in_features=384, out_features=1472, bias=False)
|
43 |
+
)
|
44 |
+
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
|
45 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
46 |
+
)
|
47 |
+
(1): T5LayerFF(
|
48 |
+
(DenseReluDense): T5DenseGatedActDense(
|
49 |
+
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
|
50 |
+
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
|
51 |
+
(wo): Linear(in_features=3584, out_features=1472, bias=False)
|
52 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
53 |
+
(act): NewGELUActivation()
|
54 |
+
)
|
55 |
+
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
|
56 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
57 |
+
)
|
58 |
+
)
|
59 |
+
)
|
60 |
+
)
|
61 |
+
(final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
|
62 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
63 |
+
)
|
64 |
+
)
|
65 |
+
)
|
66 |
+
(locked_dropout): LockedDropout(p=0.5)
|
67 |
+
(linear): Linear(in_features=1472, out_features=13, bias=True)
|
68 |
+
(loss_function): CrossEntropyLoss()
|
69 |
+
)"
|
70 |
+
2023-10-13 01:11:03,796 ----------------------------------------------------------------------------------------------------
|
71 |
+
2023-10-13 01:11:03,796 MultiCorpus: 7936 train + 992 dev + 992 test sentences
|
72 |
+
- NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr
|
73 |
+
2023-10-13 01:11:03,797 ----------------------------------------------------------------------------------------------------
|
74 |
+
2023-10-13 01:11:03,797 Train: 7936 sentences
|
75 |
+
2023-10-13 01:11:03,797 (train_with_dev=False, train_with_test=False)
|
76 |
+
2023-10-13 01:11:03,797 ----------------------------------------------------------------------------------------------------
|
77 |
+
2023-10-13 01:11:03,797 Training Params:
|
78 |
+
2023-10-13 01:11:03,797 - learning_rate: "0.00016"
|
79 |
+
2023-10-13 01:11:03,797 - mini_batch_size: "4"
|
80 |
+
2023-10-13 01:11:03,797 - max_epochs: "10"
|
81 |
+
2023-10-13 01:11:03,797 - shuffle: "True"
|
82 |
+
2023-10-13 01:11:03,797 ----------------------------------------------------------------------------------------------------
|
83 |
+
2023-10-13 01:11:03,797 Plugins:
|
84 |
+
2023-10-13 01:11:03,797 - TensorboardLogger
|
85 |
+
2023-10-13 01:11:03,797 - LinearScheduler | warmup_fraction: '0.1'
|
86 |
+
2023-10-13 01:11:03,797 ----------------------------------------------------------------------------------------------------
|
87 |
+
2023-10-13 01:11:03,797 Final evaluation on model from best epoch (best-model.pt)
|
88 |
+
2023-10-13 01:11:03,798 - metric: "('micro avg', 'f1-score')"
|
89 |
+
2023-10-13 01:11:03,798 ----------------------------------------------------------------------------------------------------
|
90 |
+
2023-10-13 01:11:03,798 Computation:
|
91 |
+
2023-10-13 01:11:03,798 - compute on device: cuda:0
|
92 |
+
2023-10-13 01:11:03,798 - embedding storage: none
|
93 |
+
2023-10-13 01:11:03,798 ----------------------------------------------------------------------------------------------------
|
94 |
+
2023-10-13 01:11:03,798 Model training base path: "hmbench-icdar/fr-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-3"
|
95 |
+
2023-10-13 01:11:03,798 ----------------------------------------------------------------------------------------------------
|
96 |
+
2023-10-13 01:11:03,798 ----------------------------------------------------------------------------------------------------
|
97 |
+
2023-10-13 01:11:03,798 Logging anything other than scalars to TensorBoard is currently not supported.
|
98 |
+
2023-10-13 01:11:57,074 epoch 1 - iter 198/1984 - loss 2.52843731 - time (sec): 53.27 - samples/sec: 301.54 - lr: 0.000016 - momentum: 0.000000
|
99 |
+
2023-10-13 01:12:49,896 epoch 1 - iter 396/1984 - loss 2.33063285 - time (sec): 106.10 - samples/sec: 299.47 - lr: 0.000032 - momentum: 0.000000
|
100 |
+
2023-10-13 01:13:43,828 epoch 1 - iter 594/1984 - loss 2.00558938 - time (sec): 160.03 - samples/sec: 304.60 - lr: 0.000048 - momentum: 0.000000
|
101 |
+
2023-10-13 01:14:37,623 epoch 1 - iter 792/1984 - loss 1.68962898 - time (sec): 213.82 - samples/sec: 305.19 - lr: 0.000064 - momentum: 0.000000
|
102 |
+
2023-10-13 01:15:32,254 epoch 1 - iter 990/1984 - loss 1.42576251 - time (sec): 268.45 - samples/sec: 305.85 - lr: 0.000080 - momentum: 0.000000
|
103 |
+
2023-10-13 01:16:30,374 epoch 1 - iter 1188/1984 - loss 1.22765584 - time (sec): 326.57 - samples/sec: 301.16 - lr: 0.000096 - momentum: 0.000000
|
104 |
+
2023-10-13 01:17:25,376 epoch 1 - iter 1386/1984 - loss 1.09207250 - time (sec): 381.58 - samples/sec: 298.82 - lr: 0.000112 - momentum: 0.000000
|
105 |
+
2023-10-13 01:18:19,155 epoch 1 - iter 1584/1984 - loss 0.98238438 - time (sec): 435.36 - samples/sec: 299.79 - lr: 0.000128 - momentum: 0.000000
|
106 |
+
2023-10-13 01:19:13,147 epoch 1 - iter 1782/1984 - loss 0.89132216 - time (sec): 489.35 - samples/sec: 301.35 - lr: 0.000144 - momentum: 0.000000
|
107 |
+
2023-10-13 01:20:07,717 epoch 1 - iter 1980/1984 - loss 0.81919035 - time (sec): 543.92 - samples/sec: 300.96 - lr: 0.000160 - momentum: 0.000000
|
108 |
+
2023-10-13 01:20:08,902 ----------------------------------------------------------------------------------------------------
|
109 |
+
2023-10-13 01:20:08,902 EPOCH 1 done: loss 0.8182 - lr: 0.000160
|
110 |
+
2023-10-13 01:20:33,569 DEV : loss 0.13464027643203735 - f1-score (micro avg) 0.6822
|
111 |
+
2023-10-13 01:20:33,608 saving best model
|
112 |
+
2023-10-13 01:20:34,548 ----------------------------------------------------------------------------------------------------
|
113 |
+
2023-10-13 01:21:27,518 epoch 2 - iter 198/1984 - loss 0.13398518 - time (sec): 52.97 - samples/sec: 317.95 - lr: 0.000158 - momentum: 0.000000
|
114 |
+
2023-10-13 01:22:20,320 epoch 2 - iter 396/1984 - loss 0.13653987 - time (sec): 105.77 - samples/sec: 312.54 - lr: 0.000156 - momentum: 0.000000
|
115 |
+
2023-10-13 01:23:13,784 epoch 2 - iter 594/1984 - loss 0.13426706 - time (sec): 159.23 - samples/sec: 309.94 - lr: 0.000155 - momentum: 0.000000
|
116 |
+
2023-10-13 01:24:07,847 epoch 2 - iter 792/1984 - loss 0.12961703 - time (sec): 213.30 - samples/sec: 310.15 - lr: 0.000153 - momentum: 0.000000
|
117 |
+
2023-10-13 01:25:00,723 epoch 2 - iter 990/1984 - loss 0.12845842 - time (sec): 266.17 - samples/sec: 308.58 - lr: 0.000151 - momentum: 0.000000
|
118 |
+
2023-10-13 01:25:57,368 epoch 2 - iter 1188/1984 - loss 0.12621724 - time (sec): 322.82 - samples/sec: 306.90 - lr: 0.000149 - momentum: 0.000000
|
119 |
+
2023-10-13 01:26:53,050 epoch 2 - iter 1386/1984 - loss 0.12382592 - time (sec): 378.50 - samples/sec: 306.09 - lr: 0.000148 - momentum: 0.000000
|
120 |
+
2023-10-13 01:27:47,084 epoch 2 - iter 1584/1984 - loss 0.12243932 - time (sec): 432.53 - samples/sec: 304.10 - lr: 0.000146 - momentum: 0.000000
|
121 |
+
2023-10-13 01:28:40,225 epoch 2 - iter 1782/1984 - loss 0.12044255 - time (sec): 485.67 - samples/sec: 303.81 - lr: 0.000144 - momentum: 0.000000
|
122 |
+
2023-10-13 01:29:33,733 epoch 2 - iter 1980/1984 - loss 0.11911028 - time (sec): 539.18 - samples/sec: 303.69 - lr: 0.000142 - momentum: 0.000000
|
123 |
+
2023-10-13 01:29:34,760 ----------------------------------------------------------------------------------------------------
|
124 |
+
2023-10-13 01:29:34,760 EPOCH 2 done: loss 0.1191 - lr: 0.000142
|
125 |
+
2023-10-13 01:30:00,644 DEV : loss 0.09056346118450165 - f1-score (micro avg) 0.7464
|
126 |
+
2023-10-13 01:30:00,691 saving best model
|
127 |
+
2023-10-13 01:30:03,443 ----------------------------------------------------------------------------------------------------
|
128 |
+
2023-10-13 01:30:58,918 epoch 3 - iter 198/1984 - loss 0.06739931 - time (sec): 55.47 - samples/sec: 309.34 - lr: 0.000140 - momentum: 0.000000
|
129 |
+
2023-10-13 01:31:51,844 epoch 3 - iter 396/1984 - loss 0.07425965 - time (sec): 108.40 - samples/sec: 306.04 - lr: 0.000139 - momentum: 0.000000
|
130 |
+
2023-10-13 01:32:45,346 epoch 3 - iter 594/1984 - loss 0.07267235 - time (sec): 161.90 - samples/sec: 302.08 - lr: 0.000137 - momentum: 0.000000
|
131 |
+
2023-10-13 01:33:40,251 epoch 3 - iter 792/1984 - loss 0.07060065 - time (sec): 216.80 - samples/sec: 298.37 - lr: 0.000135 - momentum: 0.000000
|
132 |
+
2023-10-13 01:34:34,939 epoch 3 - iter 990/1984 - loss 0.07092729 - time (sec): 271.49 - samples/sec: 299.52 - lr: 0.000133 - momentum: 0.000000
|
133 |
+
2023-10-13 01:35:31,126 epoch 3 - iter 1188/1984 - loss 0.07276706 - time (sec): 327.68 - samples/sec: 297.65 - lr: 0.000132 - momentum: 0.000000
|
134 |
+
2023-10-13 01:36:27,297 epoch 3 - iter 1386/1984 - loss 0.07298504 - time (sec): 383.85 - samples/sec: 295.50 - lr: 0.000130 - momentum: 0.000000
|
135 |
+
2023-10-13 01:37:24,493 epoch 3 - iter 1584/1984 - loss 0.07331926 - time (sec): 441.05 - samples/sec: 294.46 - lr: 0.000128 - momentum: 0.000000
|
136 |
+
2023-10-13 01:38:20,383 epoch 3 - iter 1782/1984 - loss 0.07273039 - time (sec): 496.94 - samples/sec: 294.70 - lr: 0.000126 - momentum: 0.000000
|
137 |
+
2023-10-13 01:39:13,609 epoch 3 - iter 1980/1984 - loss 0.07386661 - time (sec): 550.16 - samples/sec: 297.68 - lr: 0.000125 - momentum: 0.000000
|
138 |
+
2023-10-13 01:39:14,597 ----------------------------------------------------------------------------------------------------
|
139 |
+
2023-10-13 01:39:14,597 EPOCH 3 done: loss 0.0738 - lr: 0.000125
|
140 |
+
2023-10-13 01:39:39,918 DEV : loss 0.10628753900527954 - f1-score (micro avg) 0.7431
|
141 |
+
2023-10-13 01:39:39,957 ----------------------------------------------------------------------------------------------------
|
142 |
+
2023-10-13 01:40:34,507 epoch 4 - iter 198/1984 - loss 0.05002684 - time (sec): 54.55 - samples/sec: 319.28 - lr: 0.000123 - momentum: 0.000000
|
143 |
+
2023-10-13 01:41:28,212 epoch 4 - iter 396/1984 - loss 0.04642258 - time (sec): 108.25 - samples/sec: 306.78 - lr: 0.000121 - momentum: 0.000000
|
144 |
+
2023-10-13 01:42:24,209 epoch 4 - iter 594/1984 - loss 0.04922220 - time (sec): 164.25 - samples/sec: 300.82 - lr: 0.000119 - momentum: 0.000000
|
145 |
+
2023-10-13 01:43:20,372 epoch 4 - iter 792/1984 - loss 0.04903358 - time (sec): 220.41 - samples/sec: 298.20 - lr: 0.000117 - momentum: 0.000000
|
146 |
+
2023-10-13 01:44:16,017 epoch 4 - iter 990/1984 - loss 0.05035239 - time (sec): 276.06 - samples/sec: 297.50 - lr: 0.000116 - momentum: 0.000000
|
147 |
+
2023-10-13 01:45:10,220 epoch 4 - iter 1188/1984 - loss 0.05166238 - time (sec): 330.26 - samples/sec: 297.17 - lr: 0.000114 - momentum: 0.000000
|
148 |
+
2023-10-13 01:46:04,647 epoch 4 - iter 1386/1984 - loss 0.05299053 - time (sec): 384.69 - samples/sec: 295.60 - lr: 0.000112 - momentum: 0.000000
|
149 |
+
2023-10-13 01:46:57,739 epoch 4 - iter 1584/1984 - loss 0.05360553 - time (sec): 437.78 - samples/sec: 298.38 - lr: 0.000110 - momentum: 0.000000
|
150 |
+
2023-10-13 01:47:51,321 epoch 4 - iter 1782/1984 - loss 0.05404042 - time (sec): 491.36 - samples/sec: 298.68 - lr: 0.000109 - momentum: 0.000000
|
151 |
+
2023-10-13 01:48:46,615 epoch 4 - iter 1980/1984 - loss 0.05469939 - time (sec): 546.66 - samples/sec: 299.43 - lr: 0.000107 - momentum: 0.000000
|
152 |
+
2023-10-13 01:48:47,680 ----------------------------------------------------------------------------------------------------
|
153 |
+
2023-10-13 01:48:47,680 EPOCH 4 done: loss 0.0547 - lr: 0.000107
|
154 |
+
2023-10-13 01:49:13,494 DEV : loss 0.12986594438552856 - f1-score (micro avg) 0.7629
|
155 |
+
2023-10-13 01:49:13,542 saving best model
|
156 |
+
2023-10-13 01:49:16,237 ----------------------------------------------------------------------------------------------------
|
157 |
+
2023-10-13 01:50:11,842 epoch 5 - iter 198/1984 - loss 0.03937109 - time (sec): 55.60 - samples/sec: 279.25 - lr: 0.000105 - momentum: 0.000000
|
158 |
+
2023-10-13 01:51:04,893 epoch 5 - iter 396/1984 - loss 0.03149180 - time (sec): 108.65 - samples/sec: 293.70 - lr: 0.000103 - momentum: 0.000000
|
159 |
+
2023-10-13 01:51:57,276 epoch 5 - iter 594/1984 - loss 0.03526855 - time (sec): 161.03 - samples/sec: 300.86 - lr: 0.000101 - momentum: 0.000000
|
160 |
+
2023-10-13 01:52:48,839 epoch 5 - iter 792/1984 - loss 0.04002136 - time (sec): 212.59 - samples/sec: 299.54 - lr: 0.000100 - momentum: 0.000000
|
161 |
+
2023-10-13 01:53:41,046 epoch 5 - iter 990/1984 - loss 0.04019836 - time (sec): 264.80 - samples/sec: 299.44 - lr: 0.000098 - momentum: 0.000000
|
162 |
+
2023-10-13 01:54:33,468 epoch 5 - iter 1188/1984 - loss 0.03965078 - time (sec): 317.22 - samples/sec: 302.34 - lr: 0.000096 - momentum: 0.000000
|
163 |
+
2023-10-13 01:55:27,904 epoch 5 - iter 1386/1984 - loss 0.03976973 - time (sec): 371.66 - samples/sec: 306.05 - lr: 0.000094 - momentum: 0.000000
|
164 |
+
2023-10-13 01:56:21,617 epoch 5 - iter 1584/1984 - loss 0.03952830 - time (sec): 425.37 - samples/sec: 306.42 - lr: 0.000093 - momentum: 0.000000
|
165 |
+
2023-10-13 01:57:14,389 epoch 5 - iter 1782/1984 - loss 0.04052637 - time (sec): 478.14 - samples/sec: 306.45 - lr: 0.000091 - momentum: 0.000000
|
166 |
+
2023-10-13 01:58:06,695 epoch 5 - iter 1980/1984 - loss 0.04037425 - time (sec): 530.45 - samples/sec: 308.53 - lr: 0.000089 - momentum: 0.000000
|
167 |
+
2023-10-13 01:58:07,772 ----------------------------------------------------------------------------------------------------
|
168 |
+
2023-10-13 01:58:07,772 EPOCH 5 done: loss 0.0403 - lr: 0.000089
|
169 |
+
2023-10-13 01:58:31,953 DEV : loss 0.15890514850616455 - f1-score (micro avg) 0.7578
|
170 |
+
2023-10-13 01:58:31,995 ----------------------------------------------------------------------------------------------------
|
171 |
+
2023-10-13 01:59:24,863 epoch 6 - iter 198/1984 - loss 0.03383294 - time (sec): 52.87 - samples/sec: 307.40 - lr: 0.000087 - momentum: 0.000000
|
172 |
+
2023-10-13 02:00:17,092 epoch 6 - iter 396/1984 - loss 0.03126055 - time (sec): 105.09 - samples/sec: 306.52 - lr: 0.000085 - momentum: 0.000000
|
173 |
+
2023-10-13 02:01:09,827 epoch 6 - iter 594/1984 - loss 0.03079949 - time (sec): 157.83 - samples/sec: 309.23 - lr: 0.000084 - momentum: 0.000000
|
174 |
+
2023-10-13 02:02:02,146 epoch 6 - iter 792/1984 - loss 0.03162031 - time (sec): 210.15 - samples/sec: 311.53 - lr: 0.000082 - momentum: 0.000000
|
175 |
+
2023-10-13 02:02:54,554 epoch 6 - iter 990/1984 - loss 0.03146134 - time (sec): 262.56 - samples/sec: 312.79 - lr: 0.000080 - momentum: 0.000000
|
176 |
+
2023-10-13 02:03:46,567 epoch 6 - iter 1188/1984 - loss 0.03128278 - time (sec): 314.57 - samples/sec: 311.49 - lr: 0.000078 - momentum: 0.000000
|
177 |
+
2023-10-13 02:04:39,641 epoch 6 - iter 1386/1984 - loss 0.03149198 - time (sec): 367.64 - samples/sec: 313.24 - lr: 0.000077 - momentum: 0.000000
|
178 |
+
2023-10-13 02:05:33,650 epoch 6 - iter 1584/1984 - loss 0.02992630 - time (sec): 421.65 - samples/sec: 312.39 - lr: 0.000075 - momentum: 0.000000
|
179 |
+
2023-10-13 02:06:26,646 epoch 6 - iter 1782/1984 - loss 0.02996741 - time (sec): 474.65 - samples/sec: 312.51 - lr: 0.000073 - momentum: 0.000000
|
180 |
+
2023-10-13 02:07:18,444 epoch 6 - iter 1980/1984 - loss 0.02958364 - time (sec): 526.45 - samples/sec: 311.08 - lr: 0.000071 - momentum: 0.000000
|
181 |
+
2023-10-13 02:07:19,461 ----------------------------------------------------------------------------------------------------
|
182 |
+
2023-10-13 02:07:19,461 EPOCH 6 done: loss 0.0296 - lr: 0.000071
|
183 |
+
2023-10-13 02:07:43,565 DEV : loss 0.16922588646411896 - f1-score (micro avg) 0.7613
|
184 |
+
2023-10-13 02:07:43,608 ----------------------------------------------------------------------------------------------------
|
185 |
+
2023-10-13 02:08:34,306 epoch 7 - iter 198/1984 - loss 0.01507566 - time (sec): 50.70 - samples/sec: 318.70 - lr: 0.000069 - momentum: 0.000000
|
186 |
+
2023-10-13 02:09:25,504 epoch 7 - iter 396/1984 - loss 0.01573958 - time (sec): 101.89 - samples/sec: 323.20 - lr: 0.000068 - momentum: 0.000000
|
187 |
+
2023-10-13 02:10:18,310 epoch 7 - iter 594/1984 - loss 0.01664591 - time (sec): 154.70 - samples/sec: 316.50 - lr: 0.000066 - momentum: 0.000000
|
188 |
+
2023-10-13 02:11:10,262 epoch 7 - iter 792/1984 - loss 0.01785772 - time (sec): 206.65 - samples/sec: 316.65 - lr: 0.000064 - momentum: 0.000000
|
189 |
+
2023-10-13 02:12:01,198 epoch 7 - iter 990/1984 - loss 0.01876625 - time (sec): 257.59 - samples/sec: 316.49 - lr: 0.000062 - momentum: 0.000000
|
190 |
+
2023-10-13 02:12:52,573 epoch 7 - iter 1188/1984 - loss 0.02003134 - time (sec): 308.96 - samples/sec: 318.37 - lr: 0.000061 - momentum: 0.000000
|
191 |
+
2023-10-13 02:13:43,862 epoch 7 - iter 1386/1984 - loss 0.01967015 - time (sec): 360.25 - samples/sec: 318.42 - lr: 0.000059 - momentum: 0.000000
|
192 |
+
2023-10-13 02:14:37,995 epoch 7 - iter 1584/1984 - loss 0.02069974 - time (sec): 414.38 - samples/sec: 316.77 - lr: 0.000057 - momentum: 0.000000
|
193 |
+
2023-10-13 02:15:35,237 epoch 7 - iter 1782/1984 - loss 0.02041747 - time (sec): 471.63 - samples/sec: 312.32 - lr: 0.000055 - momentum: 0.000000
|
194 |
+
2023-10-13 02:16:29,103 epoch 7 - iter 1980/1984 - loss 0.02160503 - time (sec): 525.49 - samples/sec: 311.51 - lr: 0.000053 - momentum: 0.000000
|
195 |
+
2023-10-13 02:16:30,210 ----------------------------------------------------------------------------------------------------
|
196 |
+
2023-10-13 02:16:30,210 EPOCH 7 done: loss 0.0217 - lr: 0.000053
|
197 |
+
2023-10-13 02:16:54,770 DEV : loss 0.19541531801223755 - f1-score (micro avg) 0.7587
|
198 |
+
2023-10-13 02:16:54,810 ----------------------------------------------------------------------------------------------------
|
199 |
+
2023-10-13 02:17:51,202 epoch 8 - iter 198/1984 - loss 0.01913314 - time (sec): 56.39 - samples/sec: 293.35 - lr: 0.000052 - momentum: 0.000000
|
200 |
+
2023-10-13 02:18:47,470 epoch 8 - iter 396/1984 - loss 0.01758474 - time (sec): 112.66 - samples/sec: 283.41 - lr: 0.000050 - momentum: 0.000000
|
201 |
+
2023-10-13 02:19:44,479 epoch 8 - iter 594/1984 - loss 0.01501596 - time (sec): 169.67 - samples/sec: 287.41 - lr: 0.000048 - momentum: 0.000000
|
202 |
+
2023-10-13 02:20:38,244 epoch 8 - iter 792/1984 - loss 0.01524608 - time (sec): 223.43 - samples/sec: 293.67 - lr: 0.000046 - momentum: 0.000000
|
203 |
+
2023-10-13 02:21:28,379 epoch 8 - iter 990/1984 - loss 0.01572225 - time (sec): 273.57 - samples/sec: 299.81 - lr: 0.000045 - momentum: 0.000000
|
204 |
+
2023-10-13 02:22:18,130 epoch 8 - iter 1188/1984 - loss 0.01543476 - time (sec): 323.32 - samples/sec: 303.46 - lr: 0.000043 - momentum: 0.000000
|
205 |
+
2023-10-13 02:23:07,803 epoch 8 - iter 1386/1984 - loss 0.01514254 - time (sec): 372.99 - samples/sec: 306.00 - lr: 0.000041 - momentum: 0.000000
|
206 |
+
2023-10-13 02:23:58,125 epoch 8 - iter 1584/1984 - loss 0.01446280 - time (sec): 423.31 - samples/sec: 309.49 - lr: 0.000039 - momentum: 0.000000
|
207 |
+
2023-10-13 02:24:47,909 epoch 8 - iter 1782/1984 - loss 0.01453879 - time (sec): 473.10 - samples/sec: 310.57 - lr: 0.000037 - momentum: 0.000000
|
208 |
+
2023-10-13 02:25:39,611 epoch 8 - iter 1980/1984 - loss 0.01586744 - time (sec): 524.80 - samples/sec: 311.79 - lr: 0.000036 - momentum: 0.000000
|
209 |
+
2023-10-13 02:25:40,640 ----------------------------------------------------------------------------------------------------
|
210 |
+
2023-10-13 02:25:40,641 EPOCH 8 done: loss 0.0159 - lr: 0.000036
|
211 |
+
2023-10-13 02:26:07,441 DEV : loss 0.20716699957847595 - f1-score (micro avg) 0.7565
|
212 |
+
2023-10-13 02:26:07,484 ----------------------------------------------------------------------------------------------------
|
213 |
+
2023-10-13 02:27:01,686 epoch 9 - iter 198/1984 - loss 0.00740229 - time (sec): 54.20 - samples/sec: 285.24 - lr: 0.000034 - momentum: 0.000000
|
214 |
+
2023-10-13 02:27:55,342 epoch 9 - iter 396/1984 - loss 0.00741304 - time (sec): 107.86 - samples/sec: 286.26 - lr: 0.000032 - momentum: 0.000000
|
215 |
+
2023-10-13 02:28:48,271 epoch 9 - iter 594/1984 - loss 0.00953282 - time (sec): 160.78 - samples/sec: 293.98 - lr: 0.000030 - momentum: 0.000000
|
216 |
+
2023-10-13 02:29:41,888 epoch 9 - iter 792/1984 - loss 0.00987460 - time (sec): 214.40 - samples/sec: 299.90 - lr: 0.000029 - momentum: 0.000000
|
217 |
+
2023-10-13 02:30:34,733 epoch 9 - iter 990/1984 - loss 0.00972689 - time (sec): 267.25 - samples/sec: 302.63 - lr: 0.000027 - momentum: 0.000000
|
218 |
+
2023-10-13 02:31:26,785 epoch 9 - iter 1188/1984 - loss 0.00991641 - time (sec): 319.30 - samples/sec: 308.78 - lr: 0.000025 - momentum: 0.000000
|
219 |
+
2023-10-13 02:32:18,304 epoch 9 - iter 1386/1984 - loss 0.01028782 - time (sec): 370.82 - samples/sec: 311.33 - lr: 0.000023 - momentum: 0.000000
|
220 |
+
2023-10-13 02:33:10,088 epoch 9 - iter 1584/1984 - loss 0.01070081 - time (sec): 422.60 - samples/sec: 312.62 - lr: 0.000021 - momentum: 0.000000
|
221 |
+
2023-10-13 02:34:02,588 epoch 9 - iter 1782/1984 - loss 0.01055651 - time (sec): 475.10 - samples/sec: 312.75 - lr: 0.000020 - momentum: 0.000000
|
222 |
+
2023-10-13 02:34:54,501 epoch 9 - iter 1980/1984 - loss 0.01028953 - time (sec): 527.01 - samples/sec: 310.49 - lr: 0.000018 - momentum: 0.000000
|
223 |
+
2023-10-13 02:34:55,569 ----------------------------------------------------------------------------------------------------
|
224 |
+
2023-10-13 02:34:55,570 EPOCH 9 done: loss 0.0103 - lr: 0.000018
|
225 |
+
2023-10-13 02:35:21,677 DEV : loss 0.2197086364030838 - f1-score (micro avg) 0.7675
|
226 |
+
2023-10-13 02:35:21,722 saving best model
|
227 |
+
2023-10-13 02:35:24,408 ----------------------------------------------------------------------------------------------------
|
228 |
+
2023-10-13 02:36:16,693 epoch 10 - iter 198/1984 - loss 0.00313690 - time (sec): 52.28 - samples/sec: 315.59 - lr: 0.000016 - momentum: 0.000000
|
229 |
+
2023-10-13 02:37:09,099 epoch 10 - iter 396/1984 - loss 0.00558899 - time (sec): 104.69 - samples/sec: 317.42 - lr: 0.000014 - momentum: 0.000000
|
230 |
+
2023-10-13 02:38:01,060 epoch 10 - iter 594/1984 - loss 0.00556445 - time (sec): 156.65 - samples/sec: 319.86 - lr: 0.000013 - momentum: 0.000000
|
231 |
+
2023-10-13 02:38:53,915 epoch 10 - iter 792/1984 - loss 0.00552369 - time (sec): 209.50 - samples/sec: 315.53 - lr: 0.000011 - momentum: 0.000000
|
232 |
+
2023-10-13 02:39:46,052 epoch 10 - iter 990/1984 - loss 0.00607246 - time (sec): 261.64 - samples/sec: 315.00 - lr: 0.000009 - momentum: 0.000000
|
233 |
+
2023-10-13 02:40:39,710 epoch 10 - iter 1188/1984 - loss 0.00683260 - time (sec): 315.30 - samples/sec: 311.80 - lr: 0.000007 - momentum: 0.000000
|
234 |
+
2023-10-13 02:41:32,898 epoch 10 - iter 1386/1984 - loss 0.00736140 - time (sec): 368.49 - samples/sec: 312.14 - lr: 0.000005 - momentum: 0.000000
|
235 |
+
2023-10-13 02:42:26,307 epoch 10 - iter 1584/1984 - loss 0.00744783 - time (sec): 421.89 - samples/sec: 310.11 - lr: 0.000004 - momentum: 0.000000
|
236 |
+
2023-10-13 02:43:19,462 epoch 10 - iter 1782/1984 - loss 0.00740743 - time (sec): 475.05 - samples/sec: 311.13 - lr: 0.000002 - momentum: 0.000000
|
237 |
+
2023-10-13 02:44:11,558 epoch 10 - iter 1980/1984 - loss 0.00755919 - time (sec): 527.14 - samples/sec: 310.50 - lr: 0.000000 - momentum: 0.000000
|
238 |
+
2023-10-13 02:44:12,617 ----------------------------------------------------------------------------------------------------
|
239 |
+
2023-10-13 02:44:12,618 EPOCH 10 done: loss 0.0076 - lr: 0.000000
|
240 |
+
2023-10-13 02:44:38,438 DEV : loss 0.22709771990776062 - f1-score (micro avg) 0.769
|
241 |
+
2023-10-13 02:44:38,479 saving best model
|
242 |
+
2023-10-13 02:44:42,054 ----------------------------------------------------------------------------------------------------
|
243 |
+
2023-10-13 02:44:42,057 Loading model from best epoch ...
|
244 |
+
2023-10-13 02:44:47,171 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG
|
245 |
+
2023-10-13 02:45:11,248
|
246 |
+
Results:
|
247 |
+
- F-score (micro) 0.7627
|
248 |
+
- F-score (macro) 0.6811
|
249 |
+
- Accuracy 0.6449
|
250 |
+
|
251 |
+
By class:
|
252 |
+
precision recall f1-score support
|
253 |
+
|
254 |
+
LOC 0.7997 0.8351 0.8170 655
|
255 |
+
PER 0.6965 0.8027 0.7458 223
|
256 |
+
ORG 0.5392 0.4331 0.4803 127
|
257 |
+
|
258 |
+
micro avg 0.7488 0.7771 0.7627 1005
|
259 |
+
macro avg 0.6785 0.6903 0.6811 1005
|
260 |
+
weighted avg 0.7439 0.7771 0.7587 1005
|
261 |
+
|
262 |
+
2023-10-13 02:45:11,248 ----------------------------------------------------------------------------------------------------
|