Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,506 @@
+2023-10-25 02:46:56,140 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,141 Model: "SequenceTagger(
+  (embeddings): TransformerWordEmbeddings(
+    (model): BertModel(
+      (embeddings): BertEmbeddings(
+        (word_embeddings): Embedding(64001, 768)
+        (position_embeddings): Embedding(512, 768)
+        (token_type_embeddings): Embedding(2, 768)
+        (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+        (dropout): Dropout(p=0.1, inplace=False)
+      )
+      (encoder): BertEncoder(
+        (layer): ModuleList(
+          (0): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (1): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (2): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (3): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (4): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (5): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (6): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (7): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (8): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (9): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (10): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (11): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+        )
+      )
+      (pooler): BertPooler(
+        (dense): Linear(in_features=768, out_features=768, bias=True)
+        (activation): Tanh()
+      )
+    )
+  )
+  (locked_dropout): LockedDropout(p=0.5)
+  (linear): Linear(in_features=768, out_features=13, bias=True)
+  (loss_function): CrossEntropyLoss()
+)"
+2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,141 MultiCorpus: 5777 train + 722 dev + 723 test sentences
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/nl
+2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,141 Train:  5777 sentences
+2023-10-25 02:46:56,141         (train_with_dev=False, train_with_test=False)
+2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,141 Training Params:
+2023-10-25 02:46:56,141  - learning_rate: "5e-05" 
+2023-10-25 02:46:56,141  - mini_batch_size: "4"
+2023-10-25 02:46:56,141  - max_epochs: "10"
+2023-10-25 02:46:56,141  - shuffle: "True"
+2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,141 Plugins:
+2023-10-25 02:46:56,141  - TensorboardLogger
+2023-10-25 02:46:56,141  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,141 Final evaluation on model from best epoch (best-model.pt)
+2023-10-25 02:46:56,141  - metric: "('micro avg', 'f1-score')"
+2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,141 Computation:
+2023-10-25 02:46:56,141  - compute on device: cuda:0
+2023-10-25 02:46:56,141  - embedding storage: none
+2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,142 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
+2023-10-25 02:46:56,142 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,142 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:46:56,142 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-25 02:47:06,559 epoch 1 - iter 144/1445 - loss 1.41992500 - time (sec): 10.42 - samples/sec: 1608.70 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 02:47:16,662 epoch 1 - iter 288/1445 - loss 0.83750215 - time (sec): 20.52 - samples/sec: 1606.10 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 02:47:26,992 epoch 1 - iter 432/1445 - loss 0.61481097 - time (sec): 30.85 - samples/sec: 1627.37 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 02:47:37,751 epoch 1 - iter 576/1445 - loss 0.49739072 - time (sec): 41.61 - samples/sec: 1645.66 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 02:47:47,972 epoch 1 - iter 720/1445 - loss 0.43005049 - time (sec): 51.83 - samples/sec: 1642.73 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 02:47:58,593 epoch 1 - iter 864/1445 - loss 0.37973109 - time (sec): 62.45 - samples/sec: 1661.45 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 02:48:09,290 epoch 1 - iter 1008/1445 - loss 0.34700059 - time (sec): 73.15 - samples/sec: 1663.30 - lr: 0.000035 - momentum: 0.000000
+2023-10-25 02:48:19,641 epoch 1 - iter 1152/1445 - loss 0.32342178 - time (sec): 83.50 - samples/sec: 1663.16 - lr: 0.000040 - momentum: 0.000000
+2023-10-25 02:48:30,241 epoch 1 - iter 1296/1445 - loss 0.30192614 - time (sec): 94.10 - samples/sec: 1673.20 - lr: 0.000045 - momentum: 0.000000
+2023-10-25 02:48:41,018 epoch 1 - iter 1440/1445 - loss 0.28526748 - time (sec): 104.88 - samples/sec: 1674.11 - lr: 0.000050 - momentum: 0.000000
+2023-10-25 02:48:41,391 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:48:41,391 EPOCH 1 done: loss 0.2846 - lr: 0.000050
+2023-10-25 02:48:44,710 DEV : loss 0.1542755663394928 - f1-score (micro avg)  0.6051
+2023-10-25 02:48:44,722 saving best model
+2023-10-25 02:48:45,190 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:48:55,635 epoch 2 - iter 144/1445 - loss 0.13673856 - time (sec): 10.44 - samples/sec: 1638.04 - lr: 0.000049 - momentum: 0.000000
+2023-10-25 02:49:05,928 epoch 2 - iter 288/1445 - loss 0.12547644 - time (sec): 20.74 - samples/sec: 1655.38 - lr: 0.000049 - momentum: 0.000000
+2023-10-25 02:49:16,263 epoch 2 - iter 432/1445 - loss 0.12065053 - time (sec): 31.07 - samples/sec: 1663.96 - lr: 0.000048 - momentum: 0.000000
+2023-10-25 02:49:26,771 epoch 2 - iter 576/1445 - loss 0.11765343 - time (sec): 41.58 - samples/sec: 1664.67 - lr: 0.000048 - momentum: 0.000000
+2023-10-25 02:49:37,344 epoch 2 - iter 720/1445 - loss 0.11380688 - time (sec): 52.15 - samples/sec: 1658.88 - lr: 0.000047 - momentum: 0.000000
+2023-10-25 02:49:47,754 epoch 2 - iter 864/1445 - loss 0.10924427 - time (sec): 62.56 - samples/sec: 1659.33 - lr: 0.000047 - momentum: 0.000000
+2023-10-25 02:49:58,240 epoch 2 - iter 1008/1445 - loss 0.10937149 - time (sec): 73.05 - samples/sec: 1657.31 - lr: 0.000046 - momentum: 0.000000
+2023-10-25 02:50:08,713 epoch 2 - iter 1152/1445 - loss 0.10758530 - time (sec): 83.52 - samples/sec: 1657.90 - lr: 0.000046 - momentum: 0.000000
+2023-10-25 02:50:19,491 epoch 2 - iter 1296/1445 - loss 0.10797866 - time (sec): 94.30 - samples/sec: 1664.21 - lr: 0.000045 - momentum: 0.000000
+2023-10-25 02:50:30,412 epoch 2 - iter 1440/1445 - loss 0.10647364 - time (sec): 105.22 - samples/sec: 1669.24 - lr: 0.000044 - momentum: 0.000000
+2023-10-25 02:50:30,787 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:50:30,787 EPOCH 2 done: loss 0.1066 - lr: 0.000044
+2023-10-25 02:50:34,509 DEV : loss 0.11031629890203476 - f1-score (micro avg)  0.7728
+2023-10-25 02:50:34,521 saving best model
+2023-10-25 02:50:35,113 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:50:45,558 epoch 3 - iter 144/1445 - loss 0.07409640 - time (sec): 10.44 - samples/sec: 1639.70 - lr: 0.000044 - momentum: 0.000000
+2023-10-25 02:50:56,017 epoch 3 - iter 288/1445 - loss 0.07630135 - time (sec): 20.90 - samples/sec: 1654.39 - lr: 0.000043 - momentum: 0.000000
+2023-10-25 02:51:07,031 epoch 3 - iter 432/1445 - loss 0.08021788 - time (sec): 31.92 - samples/sec: 1679.11 - lr: 0.000043 - momentum: 0.000000
+2023-10-25 02:51:17,656 epoch 3 - iter 576/1445 - loss 0.07837193 - time (sec): 42.54 - samples/sec: 1682.70 - lr: 0.000042 - momentum: 0.000000
+2023-10-25 02:51:28,235 epoch 3 - iter 720/1445 - loss 0.07656273 - time (sec): 53.12 - samples/sec: 1688.18 - lr: 0.000042 - momentum: 0.000000
+2023-10-25 02:51:38,586 epoch 3 - iter 864/1445 - loss 0.07895927 - time (sec): 63.47 - samples/sec: 1678.32 - lr: 0.000041 - momentum: 0.000000
+2023-10-25 02:51:48,847 epoch 3 - iter 1008/1445 - loss 0.08436579 - time (sec): 73.73 - samples/sec: 1672.24 - lr: 0.000041 - momentum: 0.000000
+2023-10-25 02:51:59,241 epoch 3 - iter 1152/1445 - loss 0.09116929 - time (sec): 84.13 - samples/sec: 1671.53 - lr: 0.000040 - momentum: 0.000000
+2023-10-25 02:52:09,636 epoch 3 - iter 1296/1445 - loss 0.09128422 - time (sec): 94.52 - samples/sec: 1669.67 - lr: 0.000039 - momentum: 0.000000
+2023-10-25 02:52:20,362 epoch 3 - iter 1440/1445 - loss 0.08962111 - time (sec): 105.25 - samples/sec: 1667.25 - lr: 0.000039 - momentum: 0.000000
+2023-10-25 02:52:20,775 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:52:20,775 EPOCH 3 done: loss 0.0894 - lr: 0.000039
+2023-10-25 02:52:24,214 DEV : loss 0.11695380508899689 - f1-score (micro avg)  0.8041
+2023-10-25 02:52:24,226 saving best model
+2023-10-25 02:52:24,813 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:52:35,169 epoch 4 - iter 144/1445 - loss 0.03918180 - time (sec): 10.36 - samples/sec: 1624.10 - lr: 0.000038 - momentum: 0.000000
+2023-10-25 02:52:45,714 epoch 4 - iter 288/1445 - loss 0.04881504 - time (sec): 20.90 - samples/sec: 1665.17 - lr: 0.000038 - momentum: 0.000000
+2023-10-25 02:52:56,634 epoch 4 - iter 432/1445 - loss 0.05723016 - time (sec): 31.82 - samples/sec: 1675.80 - lr: 0.000037 - momentum: 0.000000
+2023-10-25 02:53:07,551 epoch 4 - iter 576/1445 - loss 0.05964875 - time (sec): 42.74 - samples/sec: 1662.42 - lr: 0.000037 - momentum: 0.000000
+2023-10-25 02:53:18,165 epoch 4 - iter 720/1445 - loss 0.06496166 - time (sec): 53.35 - samples/sec: 1663.62 - lr: 0.000036 - momentum: 0.000000
+2023-10-25 02:53:28,417 epoch 4 - iter 864/1445 - loss 0.06350446 - time (sec): 63.60 - samples/sec: 1657.23 - lr: 0.000036 - momentum: 0.000000
+2023-10-25 02:53:39,264 epoch 4 - iter 1008/1445 - loss 0.06051938 - time (sec): 74.45 - samples/sec: 1668.13 - lr: 0.000035 - momentum: 0.000000
+2023-10-25 02:53:49,798 epoch 4 - iter 1152/1445 - loss 0.05887437 - time (sec): 84.98 - samples/sec: 1664.26 - lr: 0.000034 - momentum: 0.000000
+2023-10-25 02:53:59,973 epoch 4 - iter 1296/1445 - loss 0.05970754 - time (sec): 95.16 - samples/sec: 1658.41 - lr: 0.000034 - momentum: 0.000000
+2023-10-25 02:54:10,424 epoch 4 - iter 1440/1445 - loss 0.06161537 - time (sec): 105.61 - samples/sec: 1665.35 - lr: 0.000033 - momentum: 0.000000
+2023-10-25 02:54:10,740 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:54:10,741 EPOCH 4 done: loss 0.0615 - lr: 0.000033
+2023-10-25 02:54:14,480 DEV : loss 0.13216571509838104 - f1-score (micro avg)  0.8015
+2023-10-25 02:54:14,492 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:54:24,879 epoch 5 - iter 144/1445 - loss 0.06199165 - time (sec): 10.39 - samples/sec: 1705.07 - lr: 0.000033 - momentum: 0.000000
+2023-10-25 02:54:35,549 epoch 5 - iter 288/1445 - loss 0.05502521 - time (sec): 21.06 - samples/sec: 1682.58 - lr: 0.000032 - momentum: 0.000000
+2023-10-25 02:54:45,983 epoch 5 - iter 432/1445 - loss 0.04870086 - time (sec): 31.49 - samples/sec: 1677.67 - lr: 0.000032 - momentum: 0.000000
+2023-10-25 02:54:56,195 epoch 5 - iter 576/1445 - loss 0.04642585 - time (sec): 41.70 - samples/sec: 1658.92 - lr: 0.000031 - momentum: 0.000000
+2023-10-25 02:55:06,571 epoch 5 - iter 720/1445 - loss 0.04392696 - time (sec): 52.08 - samples/sec: 1655.67 - lr: 0.000031 - momentum: 0.000000
+2023-10-25 02:55:17,601 epoch 5 - iter 864/1445 - loss 0.04447623 - time (sec): 63.11 - samples/sec: 1657.97 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 02:55:27,945 epoch 5 - iter 1008/1445 - loss 0.04459240 - time (sec): 73.45 - samples/sec: 1653.81 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 02:55:38,678 epoch 5 - iter 1152/1445 - loss 0.04961076 - time (sec): 84.18 - samples/sec: 1658.29 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 02:55:49,606 epoch 5 - iter 1296/1445 - loss 0.04875402 - time (sec): 95.11 - samples/sec: 1664.22 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 02:56:00,149 epoch 5 - iter 1440/1445 - loss 0.04823764 - time (sec): 105.66 - samples/sec: 1663.89 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 02:56:00,456 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:56:00,456 EPOCH 5 done: loss 0.0481 - lr: 0.000028
+2023-10-25 02:56:03,895 DEV : loss 0.17967477440834045 - f1-score (micro avg)  0.7802
+2023-10-25 02:56:03,907 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:56:14,551 epoch 6 - iter 144/1445 - loss 0.03163337 - time (sec): 10.64 - samples/sec: 1693.03 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 02:56:24,608 epoch 6 - iter 288/1445 - loss 0.03147930 - time (sec): 20.70 - samples/sec: 1646.79 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 02:56:35,463 epoch 6 - iter 432/1445 - loss 0.03580689 - time (sec): 31.56 - samples/sec: 1649.58 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 02:56:46,549 epoch 6 - iter 576/1445 - loss 0.03627773 - time (sec): 42.64 - samples/sec: 1670.01 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 02:56:57,225 epoch 6 - iter 720/1445 - loss 0.03566348 - time (sec): 53.32 - samples/sec: 1669.72 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 02:57:07,988 epoch 6 - iter 864/1445 - loss 0.03475012 - time (sec): 64.08 - samples/sec: 1668.18 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 02:57:18,683 epoch 6 - iter 1008/1445 - loss 0.03482640 - time (sec): 74.78 - samples/sec: 1666.19 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 02:57:29,048 epoch 6 - iter 1152/1445 - loss 0.03505707 - time (sec): 85.14 - samples/sec: 1665.92 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 02:57:39,148 epoch 6 - iter 1296/1445 - loss 0.03463365 - time (sec): 95.24 - samples/sec: 1662.76 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 02:57:49,762 epoch 6 - iter 1440/1445 - loss 0.03384896 - time (sec): 105.85 - samples/sec: 1660.33 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 02:57:50,108 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:57:50,109 EPOCH 6 done: loss 0.0340 - lr: 0.000022
+2023-10-25 02:57:53,734 DEV : loss 0.19392693042755127 - f1-score (micro avg)  0.7865
+2023-10-25 02:57:53,746 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:58:04,444 epoch 7 - iter 144/1445 - loss 0.02104653 - time (sec): 10.70 - samples/sec: 1703.89 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 02:58:15,335 epoch 7 - iter 288/1445 - loss 0.02262133 - time (sec): 21.59 - samples/sec: 1693.04 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 02:58:25,695 epoch 7 - iter 432/1445 - loss 0.02260463 - time (sec): 31.95 - samples/sec: 1671.25 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 02:58:36,269 epoch 7 - iter 576/1445 - loss 0.02285538 - time (sec): 42.52 - samples/sec: 1671.62 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 02:58:46,882 epoch 7 - iter 720/1445 - loss 0.02395447 - time (sec): 53.14 - samples/sec: 1666.26 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 02:58:57,348 epoch 7 - iter 864/1445 - loss 0.02356108 - time (sec): 63.60 - samples/sec: 1666.38 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 02:59:08,001 epoch 7 - iter 1008/1445 - loss 0.02380507 - time (sec): 74.25 - samples/sec: 1657.93 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 02:59:18,803 epoch 7 - iter 1152/1445 - loss 0.02353631 - time (sec): 85.06 - samples/sec: 1664.56 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 02:59:29,267 epoch 7 - iter 1296/1445 - loss 0.02194398 - time (sec): 95.52 - samples/sec: 1663.25 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 02:59:39,492 epoch 7 - iter 1440/1445 - loss 0.02210131 - time (sec): 105.75 - samples/sec: 1659.64 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 02:59:39,930 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:59:39,931 EPOCH 7 done: loss 0.0220 - lr: 0.000017
+2023-10-25 02:59:43,674 DEV : loss 0.23535600304603577 - f1-score (micro avg)  0.7756
+2023-10-25 02:59:43,687 ----------------------------------------------------------------------------------------------------
+2023-10-25 02:59:53,987 epoch 8 - iter 144/1445 - loss 0.03149949 - time (sec): 10.30 - samples/sec: 1642.87 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 03:00:04,253 epoch 8 - iter 288/1445 - loss 0.02071536 - time (sec): 20.57 - samples/sec: 1650.08 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 03:00:14,564 epoch 8 - iter 432/1445 - loss 0.01773973 - time (sec): 30.88 - samples/sec: 1634.62 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 03:00:25,173 epoch 8 - iter 576/1445 - loss 0.01610270 - time (sec): 41.49 - samples/sec: 1626.91 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 03:00:35,755 epoch 8 - iter 720/1445 - loss 0.01622486 - time (sec): 52.07 - samples/sec: 1630.60 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 03:00:46,361 epoch 8 - iter 864/1445 - loss 0.01676869 - time (sec): 62.67 - samples/sec: 1637.19 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 03:00:57,090 epoch 8 - iter 1008/1445 - loss 0.01710768 - time (sec): 73.40 - samples/sec: 1634.69 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 03:01:07,556 epoch 8 - iter 1152/1445 - loss 0.01752298 - time (sec): 83.87 - samples/sec: 1640.12 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 03:01:18,207 epoch 8 - iter 1296/1445 - loss 0.01776129 - time (sec): 94.52 - samples/sec: 1653.16 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 03:01:29,416 epoch 8 - iter 1440/1445 - loss 0.01686894 - time (sec): 105.73 - samples/sec: 1661.17 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 03:01:29,739 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:01:29,739 EPOCH 8 done: loss 0.0169 - lr: 0.000011
+2023-10-25 03:01:33,176 DEV : loss 0.18213523924350739 - f1-score (micro avg)  0.8075
+2023-10-25 03:01:33,188 saving best model
+2023-10-25 03:01:33,784 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:01:44,818 epoch 9 - iter 144/1445 - loss 0.00928022 - time (sec): 11.03 - samples/sec: 1645.09 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 03:01:55,751 epoch 9 - iter 288/1445 - loss 0.00982455 - time (sec): 21.97 - samples/sec: 1642.30 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 03:02:06,431 epoch 9 - iter 432/1445 - loss 0.00960726 - time (sec): 32.65 - samples/sec: 1673.59 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 03:02:16,942 epoch 9 - iter 576/1445 - loss 0.01120061 - time (sec): 43.16 - samples/sec: 1678.01 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 03:02:27,098 epoch 9 - iter 720/1445 - loss 0.01132071 - time (sec): 53.31 - samples/sec: 1666.57 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 03:02:37,414 epoch 9 - iter 864/1445 - loss 0.01068480 - time (sec): 63.63 - samples/sec: 1655.90 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 03:02:48,001 epoch 9 - iter 1008/1445 - loss 0.01040525 - time (sec): 74.22 - samples/sec: 1664.80 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 03:02:58,532 epoch 9 - iter 1152/1445 - loss 0.01019932 - time (sec): 84.75 - samples/sec: 1665.27 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 03:03:09,258 epoch 9 - iter 1296/1445 - loss 0.01091489 - time (sec): 95.47 - samples/sec: 1663.60 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 03:03:19,627 epoch 9 - iter 1440/1445 - loss 0.01075625 - time (sec): 105.84 - samples/sec: 1660.69 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 03:03:19,963 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:03:19,963 EPOCH 9 done: loss 0.0107 - lr: 0.000006
+2023-10-25 03:03:23,388 DEV : loss 0.170689657330513 - f1-score (micro avg)  0.8228
+2023-10-25 03:03:23,400 saving best model
+2023-10-25 03:03:23,962 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:03:34,646 epoch 10 - iter 144/1445 - loss 0.00334886 - time (sec): 10.68 - samples/sec: 1665.67 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 03:03:45,380 epoch 10 - iter 288/1445 - loss 0.00315989 - time (sec): 21.42 - samples/sec: 1672.04 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 03:03:55,756 epoch 10 - iter 432/1445 - loss 0.00562550 - time (sec): 31.79 - samples/sec: 1651.83 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 03:04:06,159 epoch 10 - iter 576/1445 - loss 0.00612415 - time (sec): 42.20 - samples/sec: 1646.36 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 03:04:16,580 epoch 10 - iter 720/1445 - loss 0.00595122 - time (sec): 52.62 - samples/sec: 1645.55 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 03:04:26,978 epoch 10 - iter 864/1445 - loss 0.00564152 - time (sec): 63.02 - samples/sec: 1654.45 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 03:04:37,572 epoch 10 - iter 1008/1445 - loss 0.00580851 - time (sec): 73.61 - samples/sec: 1649.51 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 03:04:48,061 epoch 10 - iter 1152/1445 - loss 0.00639612 - time (sec): 84.10 - samples/sec: 1643.68 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 03:04:58,876 epoch 10 - iter 1296/1445 - loss 0.00636865 - time (sec): 94.91 - samples/sec: 1649.65 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 03:05:09,697 epoch 10 - iter 1440/1445 - loss 0.00635474 - time (sec): 105.73 - samples/sec: 1660.15 - lr: 0.000000 - momentum: 0.000000
+2023-10-25 03:05:10,044 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:05:10,044 EPOCH 10 done: loss 0.0065 - lr: 0.000000
+2023-10-25 03:05:13,783 DEV : loss 0.2022934854030609 - f1-score (micro avg)  0.8098
+2023-10-25 03:05:14,262 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:05:14,263 Loading model from best epoch ...
+2023-10-25 03:05:15,995 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
+2023-10-25 03:05:19,560 
+Results:
+- F-score (micro) 0.8085
+- F-score (macro) 0.7092
+- Accuracy 0.6905
+
+By class:
+              precision    recall  f1-score   support
+
+         PER     0.8294    0.7967    0.8127       482
+         LOC     0.8900    0.8122    0.8493       458
+         ORG     0.5745    0.3913    0.4655        69
+
+   micro avg     0.8438    0.7760    0.8085      1009
+   macro avg     0.7646    0.6667    0.7092      1009
+weighted avg     0.8394    0.7760    0.8056      1009
+
+2023-10-25 03:05:19,560 ----------------------------------------------------------------------------------------------------