Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,507 @@
+2023-10-24 22:13:21,924 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,925 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()
+)"
+2023-10-24 22:13:21,925 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 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
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 Train:  5777 sentences
+2023-10-24 22:13:21,926         (train_with_dev=False, train_with_test=False)
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 Training Params:
+2023-10-24 22:13:21,926  - learning_rate: "5e-05" 
+2023-10-24 22:13:21,926  - mini_batch_size: "4"
+2023-10-24 22:13:21,926  - max_epochs: "10"
+2023-10-24 22:13:21,926  - shuffle: "True"
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 Plugins:
+2023-10-24 22:13:21,926  - TensorboardLogger
+2023-10-24 22:13:21,926  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 Final evaluation on model from best epoch (best-model.pt)
+2023-10-24 22:13:21,926  - metric: "('micro avg', 'f1-score')"
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 Computation:
+2023-10-24 22:13:21,926  - compute on device: cuda:0
+2023-10-24 22:13:21,926  - embedding storage: none
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:13:21,926 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-24 22:13:32,380 epoch 1 - iter 144/1445 - loss 1.49559085 - time (sec): 10.45 - samples/sec: 1692.34 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 22:13:42,853 epoch 1 - iter 288/1445 - loss 0.87195492 - time (sec): 20.93 - samples/sec: 1683.05 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 22:13:53,683 epoch 1 - iter 432/1445 - loss 0.64108177 - time (sec): 31.76 - samples/sec: 1704.94 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 22:14:03,881 epoch 1 - iter 576/1445 - loss 0.53043413 - time (sec): 41.95 - samples/sec: 1681.07 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 22:14:14,069 epoch 1 - iter 720/1445 - loss 0.45645493 - time (sec): 52.14 - samples/sec: 1671.29 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 22:14:24,447 epoch 1 - iter 864/1445 - loss 0.40865665 - time (sec): 62.52 - samples/sec: 1666.71 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 22:14:34,689 epoch 1 - iter 1008/1445 - loss 0.37243246 - time (sec): 72.76 - samples/sec: 1660.47 - lr: 0.000035 - momentum: 0.000000
+2023-10-24 22:14:45,375 epoch 1 - iter 1152/1445 - loss 0.34345336 - time (sec): 83.45 - samples/sec: 1663.95 - lr: 0.000040 - momentum: 0.000000
+2023-10-24 22:14:55,909 epoch 1 - iter 1296/1445 - loss 0.31896611 - time (sec): 93.98 - samples/sec: 1671.51 - lr: 0.000045 - momentum: 0.000000
+2023-10-24 22:15:06,686 epoch 1 - iter 1440/1445 - loss 0.29904032 - time (sec): 104.76 - samples/sec: 1677.73 - lr: 0.000050 - momentum: 0.000000
+2023-10-24 22:15:07,000 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:15:07,001 EPOCH 1 done: loss 0.2986 - lr: 0.000050
+2023-10-24 22:15:10,276 DEV : loss 0.1465490758419037 - f1-score (micro avg)  0.4443
+2023-10-24 22:15:10,288 saving best model
+2023-10-24 22:15:10,842 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:15:21,246 epoch 2 - iter 144/1445 - loss 0.11682404 - time (sec): 10.40 - samples/sec: 1638.60 - lr: 0.000049 - momentum: 0.000000
+2023-10-24 22:15:31,373 epoch 2 - iter 288/1445 - loss 0.11667509 - time (sec): 20.53 - samples/sec: 1627.84 - lr: 0.000049 - momentum: 0.000000
+2023-10-24 22:15:41,772 epoch 2 - iter 432/1445 - loss 0.11315670 - time (sec): 30.93 - samples/sec: 1636.53 - lr: 0.000048 - momentum: 0.000000
+2023-10-24 22:15:52,605 epoch 2 - iter 576/1445 - loss 0.11090746 - time (sec): 41.76 - samples/sec: 1658.63 - lr: 0.000048 - momentum: 0.000000
+2023-10-24 22:16:03,567 epoch 2 - iter 720/1445 - loss 0.10511821 - time (sec): 52.72 - samples/sec: 1678.85 - lr: 0.000047 - momentum: 0.000000
+2023-10-24 22:16:14,590 epoch 2 - iter 864/1445 - loss 0.10350836 - time (sec): 63.75 - samples/sec: 1683.22 - lr: 0.000047 - momentum: 0.000000
+2023-10-24 22:16:24,933 epoch 2 - iter 1008/1445 - loss 0.10362581 - time (sec): 74.09 - samples/sec: 1679.79 - lr: 0.000046 - momentum: 0.000000
+2023-10-24 22:16:34,883 epoch 2 - iter 1152/1445 - loss 0.10658382 - time (sec): 84.04 - samples/sec: 1669.01 - lr: 0.000046 - momentum: 0.000000
+2023-10-24 22:16:45,346 epoch 2 - iter 1296/1445 - loss 0.10667648 - time (sec): 94.50 - samples/sec: 1667.31 - lr: 0.000045 - momentum: 0.000000
+2023-10-24 22:16:55,925 epoch 2 - iter 1440/1445 - loss 0.10680059 - time (sec): 105.08 - samples/sec: 1670.92 - lr: 0.000044 - momentum: 0.000000
+2023-10-24 22:16:56,251 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:16:56,251 EPOCH 2 done: loss 0.1070 - lr: 0.000044
+2023-10-24 22:16:59,958 DEV : loss 0.10742148011922836 - f1-score (micro avg)  0.7828
+2023-10-24 22:16:59,970 saving best model
+2023-10-24 22:17:00,625 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:17:11,142 epoch 3 - iter 144/1445 - loss 0.07888928 - time (sec): 10.52 - samples/sec: 1662.49 - lr: 0.000044 - momentum: 0.000000
+2023-10-24 22:17:21,593 epoch 3 - iter 288/1445 - loss 0.06951416 - time (sec): 20.97 - samples/sec: 1667.45 - lr: 0.000043 - momentum: 0.000000
+2023-10-24 22:17:31,937 epoch 3 - iter 432/1445 - loss 0.07610488 - time (sec): 31.31 - samples/sec: 1669.25 - lr: 0.000043 - momentum: 0.000000
+2023-10-24 22:17:42,638 epoch 3 - iter 576/1445 - loss 0.07378191 - time (sec): 42.01 - samples/sec: 1677.25 - lr: 0.000042 - momentum: 0.000000
+2023-10-24 22:17:53,220 epoch 3 - iter 720/1445 - loss 0.07592950 - time (sec): 52.59 - samples/sec: 1677.29 - lr: 0.000042 - momentum: 0.000000
+2023-10-24 22:18:04,012 epoch 3 - iter 864/1445 - loss 0.08537831 - time (sec): 63.39 - samples/sec: 1688.53 - lr: 0.000041 - momentum: 0.000000
+2023-10-24 22:18:14,355 epoch 3 - iter 1008/1445 - loss 0.09120584 - time (sec): 73.73 - samples/sec: 1674.36 - lr: 0.000041 - momentum: 0.000000
+2023-10-24 22:18:24,684 epoch 3 - iter 1152/1445 - loss 0.08969195 - time (sec): 84.06 - samples/sec: 1666.85 - lr: 0.000040 - momentum: 0.000000
+2023-10-24 22:18:35,249 epoch 3 - iter 1296/1445 - loss 0.08985953 - time (sec): 94.62 - samples/sec: 1667.96 - lr: 0.000039 - momentum: 0.000000
+2023-10-24 22:18:45,949 epoch 3 - iter 1440/1445 - loss 0.09136075 - time (sec): 105.32 - samples/sec: 1670.01 - lr: 0.000039 - momentum: 0.000000
+2023-10-24 22:18:46,238 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:18:46,239 EPOCH 3 done: loss 0.0915 - lr: 0.000039
+2023-10-24 22:18:49,660 DEV : loss 0.11891528218984604 - f1-score (micro avg)  0.796
+2023-10-24 22:18:49,672 saving best model
+2023-10-24 22:18:50,385 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:19:00,748 epoch 4 - iter 144/1445 - loss 0.05647820 - time (sec): 10.36 - samples/sec: 1688.59 - lr: 0.000038 - momentum: 0.000000
+2023-10-24 22:19:11,515 epoch 4 - iter 288/1445 - loss 0.05815810 - time (sec): 21.13 - samples/sec: 1643.99 - lr: 0.000038 - momentum: 0.000000
+2023-10-24 22:19:21,630 epoch 4 - iter 432/1445 - loss 0.06297138 - time (sec): 31.24 - samples/sec: 1623.46 - lr: 0.000037 - momentum: 0.000000
+2023-10-24 22:19:31,956 epoch 4 - iter 576/1445 - loss 0.06251057 - time (sec): 41.57 - samples/sec: 1617.67 - lr: 0.000037 - momentum: 0.000000
+2023-10-24 22:19:42,685 epoch 4 - iter 720/1445 - loss 0.06294971 - time (sec): 52.30 - samples/sec: 1641.43 - lr: 0.000036 - momentum: 0.000000
+2023-10-24 22:19:53,347 epoch 4 - iter 864/1445 - loss 0.06501619 - time (sec): 62.96 - samples/sec: 1652.80 - lr: 0.000036 - momentum: 0.000000
+2023-10-24 22:20:04,252 epoch 4 - iter 1008/1445 - loss 0.06499533 - time (sec): 73.87 - samples/sec: 1658.53 - lr: 0.000035 - momentum: 0.000000
+2023-10-24 22:20:14,785 epoch 4 - iter 1152/1445 - loss 0.06307111 - time (sec): 84.40 - samples/sec: 1664.21 - lr: 0.000034 - momentum: 0.000000
+2023-10-24 22:20:25,350 epoch 4 - iter 1296/1445 - loss 0.06234630 - time (sec): 94.96 - samples/sec: 1664.27 - lr: 0.000034 - momentum: 0.000000
+2023-10-24 22:20:35,838 epoch 4 - iter 1440/1445 - loss 0.06175381 - time (sec): 105.45 - samples/sec: 1667.05 - lr: 0.000033 - momentum: 0.000000
+2023-10-24 22:20:36,143 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:20:36,144 EPOCH 4 done: loss 0.0619 - lr: 0.000033
+2023-10-24 22:20:39,556 DEV : loss 0.1823125034570694 - f1-score (micro avg)  0.756
+2023-10-24 22:20:39,567 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:20:50,308 epoch 5 - iter 144/1445 - loss 0.05559863 - time (sec): 10.74 - samples/sec: 1703.77 - lr: 0.000033 - momentum: 0.000000
+2023-10-24 22:21:01,046 epoch 5 - iter 288/1445 - loss 0.05287999 - time (sec): 21.48 - samples/sec: 1666.13 - lr: 0.000032 - momentum: 0.000000
+2023-10-24 22:21:11,592 epoch 5 - iter 432/1445 - loss 0.04559996 - time (sec): 32.02 - samples/sec: 1666.25 - lr: 0.000032 - momentum: 0.000000
+2023-10-24 22:21:22,613 epoch 5 - iter 576/1445 - loss 0.04653938 - time (sec): 43.04 - samples/sec: 1678.93 - lr: 0.000031 - momentum: 0.000000
+2023-10-24 22:21:32,932 epoch 5 - iter 720/1445 - loss 0.04780450 - time (sec): 53.36 - samples/sec: 1676.43 - lr: 0.000031 - momentum: 0.000000
+2023-10-24 22:21:43,617 epoch 5 - iter 864/1445 - loss 0.04662656 - time (sec): 64.05 - samples/sec: 1680.93 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 22:21:53,610 epoch 5 - iter 1008/1445 - loss 0.04653849 - time (sec): 74.04 - samples/sec: 1668.59 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 22:22:04,090 epoch 5 - iter 1152/1445 - loss 0.04554055 - time (sec): 84.52 - samples/sec: 1673.76 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 22:22:14,414 epoch 5 - iter 1296/1445 - loss 0.04549864 - time (sec): 94.85 - samples/sec: 1665.47 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 22:22:24,915 epoch 5 - iter 1440/1445 - loss 0.04622108 - time (sec): 105.35 - samples/sec: 1665.43 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 22:22:25,341 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:22:25,342 EPOCH 5 done: loss 0.0462 - lr: 0.000028
+2023-10-24 22:22:29,053 DEV : loss 0.14015598595142365 - f1-score (micro avg)  0.8063
+2023-10-24 22:22:29,065 saving best model
+2023-10-24 22:22:29,718 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:22:40,293 epoch 6 - iter 144/1445 - loss 0.02737257 - time (sec): 10.57 - samples/sec: 1620.84 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 22:22:50,766 epoch 6 - iter 288/1445 - loss 0.02987116 - time (sec): 21.05 - samples/sec: 1632.47 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 22:23:01,736 epoch 6 - iter 432/1445 - loss 0.03340606 - time (sec): 32.02 - samples/sec: 1665.29 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 22:23:12,193 epoch 6 - iter 576/1445 - loss 0.03514036 - time (sec): 42.47 - samples/sec: 1652.48 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 22:23:22,643 epoch 6 - iter 720/1445 - loss 0.03531426 - time (sec): 52.92 - samples/sec: 1650.42 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 22:23:33,304 epoch 6 - iter 864/1445 - loss 0.03610013 - time (sec): 63.58 - samples/sec: 1655.96 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 22:23:43,755 epoch 6 - iter 1008/1445 - loss 0.03512300 - time (sec): 74.04 - samples/sec: 1666.00 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 22:23:54,257 epoch 6 - iter 1152/1445 - loss 0.03710725 - time (sec): 84.54 - samples/sec: 1666.00 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 22:24:04,699 epoch 6 - iter 1296/1445 - loss 0.03585885 - time (sec): 94.98 - samples/sec: 1669.28 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 22:24:15,046 epoch 6 - iter 1440/1445 - loss 0.03557740 - time (sec): 105.33 - samples/sec: 1667.87 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 22:24:15,381 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:24:15,382 EPOCH 6 done: loss 0.0355 - lr: 0.000022
+2023-10-24 22:24:18,806 DEV : loss 0.18115007877349854 - f1-score (micro avg)  0.786
+2023-10-24 22:24:18,817 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:24:29,308 epoch 7 - iter 144/1445 - loss 0.02078286 - time (sec): 10.49 - samples/sec: 1705.63 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 22:24:39,999 epoch 7 - iter 288/1445 - loss 0.02962769 - time (sec): 21.18 - samples/sec: 1669.68 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 22:24:50,656 epoch 7 - iter 432/1445 - loss 0.02907881 - time (sec): 31.84 - samples/sec: 1653.22 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 22:25:01,260 epoch 7 - iter 576/1445 - loss 0.03114169 - time (sec): 42.44 - samples/sec: 1670.16 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 22:25:12,090 epoch 7 - iter 720/1445 - loss 0.02943001 - time (sec): 53.27 - samples/sec: 1672.86 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 22:25:22,358 epoch 7 - iter 864/1445 - loss 0.02860415 - time (sec): 63.54 - samples/sec: 1658.11 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 22:25:32,771 epoch 7 - iter 1008/1445 - loss 0.02721034 - time (sec): 73.95 - samples/sec: 1654.20 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 22:25:43,289 epoch 7 - iter 1152/1445 - loss 0.02659125 - time (sec): 84.47 - samples/sec: 1655.55 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 22:25:53,971 epoch 7 - iter 1296/1445 - loss 0.02604572 - time (sec): 95.15 - samples/sec: 1660.84 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 22:26:04,502 epoch 7 - iter 1440/1445 - loss 0.02528759 - time (sec): 105.68 - samples/sec: 1661.04 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 22:26:04,906 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:26:04,906 EPOCH 7 done: loss 0.0252 - lr: 0.000017
+2023-10-24 22:26:08,329 DEV : loss 0.19167011976242065 - f1-score (micro avg)  0.811
+2023-10-24 22:26:08,341 saving best model
+2023-10-24 22:26:08,996 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:26:19,544 epoch 8 - iter 144/1445 - loss 0.01368515 - time (sec): 10.55 - samples/sec: 1673.27 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 22:26:30,355 epoch 8 - iter 288/1445 - loss 0.01538066 - time (sec): 21.36 - samples/sec: 1660.55 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 22:26:40,676 epoch 8 - iter 432/1445 - loss 0.01436584 - time (sec): 31.68 - samples/sec: 1675.14 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 22:26:51,893 epoch 8 - iter 576/1445 - loss 0.01432006 - time (sec): 42.90 - samples/sec: 1706.24 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 22:27:02,324 epoch 8 - iter 720/1445 - loss 0.01409563 - time (sec): 53.33 - samples/sec: 1691.08 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 22:27:12,778 epoch 8 - iter 864/1445 - loss 0.01487126 - time (sec): 63.78 - samples/sec: 1688.73 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 22:27:23,350 epoch 8 - iter 1008/1445 - loss 0.01619878 - time (sec): 74.35 - samples/sec: 1681.67 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 22:27:33,298 epoch 8 - iter 1152/1445 - loss 0.01597473 - time (sec): 84.30 - samples/sec: 1663.50 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 22:27:43,579 epoch 8 - iter 1296/1445 - loss 0.01520411 - time (sec): 94.58 - samples/sec: 1661.71 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 22:27:54,314 epoch 8 - iter 1440/1445 - loss 0.01673962 - time (sec): 105.32 - samples/sec: 1666.43 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 22:27:54,743 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:27:54,744 EPOCH 8 done: loss 0.0167 - lr: 0.000011
+2023-10-24 22:27:58,460 DEV : loss 0.20966801047325134 - f1-score (micro avg)  0.8068
+2023-10-24 22:27:58,472 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:28:09,302 epoch 9 - iter 144/1445 - loss 0.00335298 - time (sec): 10.83 - samples/sec: 1730.28 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 22:28:19,408 epoch 9 - iter 288/1445 - loss 0.00713944 - time (sec): 20.93 - samples/sec: 1674.71 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 22:28:30,389 epoch 9 - iter 432/1445 - loss 0.00831560 - time (sec): 31.92 - samples/sec: 1677.91 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 22:28:40,925 epoch 9 - iter 576/1445 - loss 0.01125306 - time (sec): 42.45 - samples/sec: 1673.19 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 22:28:51,398 epoch 9 - iter 720/1445 - loss 0.01066392 - time (sec): 52.92 - samples/sec: 1668.82 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 22:29:01,925 epoch 9 - iter 864/1445 - loss 0.00979328 - time (sec): 63.45 - samples/sec: 1673.13 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 22:29:12,556 epoch 9 - iter 1008/1445 - loss 0.01050402 - time (sec): 74.08 - samples/sec: 1673.14 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 22:29:22,908 epoch 9 - iter 1152/1445 - loss 0.01017532 - time (sec): 84.43 - samples/sec: 1671.11 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 22:29:33,357 epoch 9 - iter 1296/1445 - loss 0.00941237 - time (sec): 94.88 - samples/sec: 1670.19 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 22:29:43,936 epoch 9 - iter 1440/1445 - loss 0.00966527 - time (sec): 105.46 - samples/sec: 1667.23 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 22:29:44,236 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:29:44,236 EPOCH 9 done: loss 0.0096 - lr: 0.000006
+2023-10-24 22:29:47,661 DEV : loss 0.22105184197425842 - f1-score (micro avg)  0.8086
+2023-10-24 22:29:47,672 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:29:58,237 epoch 10 - iter 144/1445 - loss 0.00621614 - time (sec): 10.56 - samples/sec: 1652.08 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 22:30:08,967 epoch 10 - iter 288/1445 - loss 0.01088022 - time (sec): 21.29 - samples/sec: 1667.64 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 22:30:19,753 epoch 10 - iter 432/1445 - loss 0.00891142 - time (sec): 32.08 - samples/sec: 1697.21 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 22:30:30,666 epoch 10 - iter 576/1445 - loss 0.00890582 - time (sec): 42.99 - samples/sec: 1693.35 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 22:30:40,999 epoch 10 - iter 720/1445 - loss 0.00818322 - time (sec): 53.33 - samples/sec: 1679.18 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 22:30:51,571 epoch 10 - iter 864/1445 - loss 0.00748506 - time (sec): 63.90 - samples/sec: 1671.13 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 22:31:02,171 epoch 10 - iter 1008/1445 - loss 0.00750558 - time (sec): 74.50 - samples/sec: 1666.22 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 22:31:12,576 epoch 10 - iter 1152/1445 - loss 0.00743769 - time (sec): 84.90 - samples/sec: 1667.05 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 22:31:23,189 epoch 10 - iter 1296/1445 - loss 0.00721825 - time (sec): 95.52 - samples/sec: 1661.21 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 22:31:33,509 epoch 10 - iter 1440/1445 - loss 0.00720286 - time (sec): 105.84 - samples/sec: 1661.25 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 22:31:33,805 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:31:33,805 EPOCH 10 done: loss 0.0072 - lr: 0.000000
+2023-10-24 22:31:37,236 DEV : loss 0.22644661366939545 - f1-score (micro avg)  0.8158
+2023-10-24 22:31:37,249 saving best model
+2023-10-24 22:31:38,458 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:31:38,459 Loading model from best epoch ...
+2023-10-24 22:31:40,317 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
+2023-10-24 22:31:43,856 
+Results:
+- F-score (micro) 0.7971
+- F-score (macro) 0.6618
+- Accuracy 0.678
+
+By class:
+              precision    recall  f1-score   support
+
+         PER     0.8545    0.7676    0.8087       482
+         LOC     0.8913    0.8057    0.8463       458
+         ORG     0.4130    0.2754    0.3304        69
+
+   micro avg     0.8488    0.7512    0.7971      1009
+   macro avg     0.7196    0.6162    0.6618      1009
+weighted avg     0.8410    0.7512    0.7931      1009
+
+2023-10-24 22:31:43,856 ----------------------------------------------------------------------------------------------------