Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,506 @@
+2023-10-24 21:54:39,743 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,744 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 21:54:39,744 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,744 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 21:54:39,744 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,744 Train:  5777 sentences
+2023-10-24 21:54:39,745         (train_with_dev=False, train_with_test=False)
+2023-10-24 21:54:39,745 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,745 Training Params:
+2023-10-24 21:54:39,745  - learning_rate: "3e-05" 
+2023-10-24 21:54:39,745  - mini_batch_size: "4"
+2023-10-24 21:54:39,745  - max_epochs: "10"
+2023-10-24 21:54:39,745  - shuffle: "True"
+2023-10-24 21:54:39,745 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,745 Plugins:
+2023-10-24 21:54:39,745  - TensorboardLogger
+2023-10-24 21:54:39,745  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-24 21:54:39,745 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,745 Final evaluation on model from best epoch (best-model.pt)
+2023-10-24 21:54:39,745  - metric: "('micro avg', 'f1-score')"
+2023-10-24 21:54:39,745 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,745 Computation:
+2023-10-24 21:54:39,745  - compute on device: cuda:0
+2023-10-24 21:54:39,745  - embedding storage: none
+2023-10-24 21:54:39,745 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,745 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
+2023-10-24 21:54:39,745 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,745 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:54:39,745 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-24 21:54:50,587 epoch 1 - iter 144/1445 - loss 1.81376766 - time (sec): 10.84 - samples/sec: 1631.80 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 21:55:00,870 epoch 1 - iter 288/1445 - loss 1.04845476 - time (sec): 21.12 - samples/sec: 1667.24 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 21:55:11,485 epoch 1 - iter 432/1445 - loss 0.76140912 - time (sec): 31.74 - samples/sec: 1705.82 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 21:55:21,493 epoch 1 - iter 576/1445 - loss 0.62525491 - time (sec): 41.75 - samples/sec: 1689.38 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 21:55:31,497 epoch 1 - iter 720/1445 - loss 0.53447084 - time (sec): 51.75 - samples/sec: 1683.91 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 21:55:41,710 epoch 1 - iter 864/1445 - loss 0.47506408 - time (sec): 61.96 - samples/sec: 1681.67 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 21:55:51,795 epoch 1 - iter 1008/1445 - loss 0.43026392 - time (sec): 72.05 - samples/sec: 1676.91 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 21:56:02,312 epoch 1 - iter 1152/1445 - loss 0.39358120 - time (sec): 82.57 - samples/sec: 1681.72 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 21:56:12,669 epoch 1 - iter 1296/1445 - loss 0.36332737 - time (sec): 92.92 - samples/sec: 1690.57 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 21:56:23,299 epoch 1 - iter 1440/1445 - loss 0.33854273 - time (sec): 103.55 - samples/sec: 1697.27 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 21:56:23,610 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:56:23,610 EPOCH 1 done: loss 0.3381 - lr: 0.000030
+2023-10-24 21:56:26,809 DEV : loss 0.16900984942913055 - f1-score (micro avg)  0.3766
+2023-10-24 21:56:26,820 saving best model
+2023-10-24 21:56:27,384 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:56:37,658 epoch 2 - iter 144/1445 - loss 0.11826824 - time (sec): 10.27 - samples/sec: 1659.46 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 21:56:47,685 epoch 2 - iter 288/1445 - loss 0.11630277 - time (sec): 20.30 - samples/sec: 1646.32 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 21:56:57,995 epoch 2 - iter 432/1445 - loss 0.11271448 - time (sec): 30.61 - samples/sec: 1653.63 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 21:57:08,734 epoch 2 - iter 576/1445 - loss 0.10875524 - time (sec): 41.35 - samples/sec: 1675.21 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 21:57:19,614 epoch 2 - iter 720/1445 - loss 0.10283488 - time (sec): 52.23 - samples/sec: 1694.77 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 21:57:30,574 epoch 2 - iter 864/1445 - loss 0.10133854 - time (sec): 63.19 - samples/sec: 1698.08 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 21:57:40,866 epoch 2 - iter 1008/1445 - loss 0.10017031 - time (sec): 73.48 - samples/sec: 1693.71 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 21:57:50,757 epoch 2 - iter 1152/1445 - loss 0.10315088 - time (sec): 83.37 - samples/sec: 1682.40 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 21:58:01,154 epoch 2 - iter 1296/1445 - loss 0.10336237 - time (sec): 93.77 - samples/sec: 1680.38 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 21:58:11,679 epoch 2 - iter 1440/1445 - loss 0.10342005 - time (sec): 104.29 - samples/sec: 1683.55 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 21:58:12,004 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:58:12,004 EPOCH 2 done: loss 0.1035 - lr: 0.000027
+2023-10-24 21:58:15,677 DEV : loss 0.1034025326371193 - f1-score (micro avg)  0.8052
+2023-10-24 21:58:15,689 saving best model
+2023-10-24 21:58:16,491 ----------------------------------------------------------------------------------------------------
+2023-10-24 21:58:26,986 epoch 3 - iter 144/1445 - loss 0.07272831 - time (sec): 10.49 - samples/sec: 1666.02 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 21:58:37,393 epoch 3 - iter 288/1445 - loss 0.06637558 - time (sec): 20.90 - samples/sec: 1672.71 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 21:58:47,702 epoch 3 - iter 432/1445 - loss 0.07131592 - time (sec): 31.21 - samples/sec: 1674.66 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 21:58:58,388 epoch 3 - iter 576/1445 - loss 0.06974866 - time (sec): 41.90 - samples/sec: 1681.94 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 21:59:08,950 epoch 3 - iter 720/1445 - loss 0.06896857 - time (sec): 52.46 - samples/sec: 1681.63 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 21:59:19,705 epoch 3 - iter 864/1445 - loss 0.07063252 - time (sec): 63.21 - samples/sec: 1693.15 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 21:59:30,022 epoch 3 - iter 1008/1445 - loss 0.07103855 - time (sec): 73.53 - samples/sec: 1678.89 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 21:59:40,341 epoch 3 - iter 1152/1445 - loss 0.07115340 - time (sec): 83.85 - samples/sec: 1671.02 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 21:59:50,899 epoch 3 - iter 1296/1445 - loss 0.07080450 - time (sec): 94.41 - samples/sec: 1671.77 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 22:00:01,593 epoch 3 - iter 1440/1445 - loss 0.07048554 - time (sec): 105.10 - samples/sec: 1673.54 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 22:00:01,884 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:00:01,884 EPOCH 3 done: loss 0.0706 - lr: 0.000023
+2023-10-24 22:00:05,309 DEV : loss 0.10592877864837646 - f1-score (micro avg)  0.8065
+2023-10-24 22:00:05,321 saving best model
+2023-10-24 22:00:06,098 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:00:16,449 epoch 4 - iter 144/1445 - loss 0.04420143 - time (sec): 10.35 - samples/sec: 1690.62 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 22:00:26,906 epoch 4 - iter 288/1445 - loss 0.05211392 - time (sec): 20.81 - samples/sec: 1669.44 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 22:00:37,283 epoch 4 - iter 432/1445 - loss 0.05533820 - time (sec): 31.18 - samples/sec: 1626.59 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 22:00:47,604 epoch 4 - iter 576/1445 - loss 0.05568201 - time (sec): 41.51 - samples/sec: 1620.21 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 22:00:58,327 epoch 4 - iter 720/1445 - loss 0.05465541 - time (sec): 52.23 - samples/sec: 1643.67 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 22:01:08,980 epoch 4 - iter 864/1445 - loss 0.05576727 - time (sec): 62.88 - samples/sec: 1654.90 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 22:01:19,883 epoch 4 - iter 1008/1445 - loss 0.05481408 - time (sec): 73.78 - samples/sec: 1660.38 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 22:01:30,417 epoch 4 - iter 1152/1445 - loss 0.05383623 - time (sec): 84.32 - samples/sec: 1665.80 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 22:01:40,977 epoch 4 - iter 1296/1445 - loss 0.05292807 - time (sec): 94.88 - samples/sec: 1665.78 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 22:01:51,448 epoch 4 - iter 1440/1445 - loss 0.05208862 - time (sec): 105.35 - samples/sec: 1668.68 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 22:01:51,753 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:01:51,753 EPOCH 4 done: loss 0.0521 - lr: 0.000020
+2023-10-24 22:01:55,170 DEV : loss 0.1245899349451065 - f1-score (micro avg)  0.8002
+2023-10-24 22:01:55,181 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:02:05,922 epoch 5 - iter 144/1445 - loss 0.03735872 - time (sec): 10.74 - samples/sec: 1703.86 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 22:02:16,659 epoch 5 - iter 288/1445 - loss 0.04258998 - time (sec): 21.48 - samples/sec: 1666.21 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 22:02:27,208 epoch 5 - iter 432/1445 - loss 0.03756029 - time (sec): 32.03 - samples/sec: 1666.14 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 22:02:38,230 epoch 5 - iter 576/1445 - loss 0.03855021 - time (sec): 43.05 - samples/sec: 1678.82 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 22:02:48,549 epoch 5 - iter 720/1445 - loss 0.04032539 - time (sec): 53.37 - samples/sec: 1676.33 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 22:02:59,250 epoch 5 - iter 864/1445 - loss 0.04038091 - time (sec): 64.07 - samples/sec: 1680.42 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 22:03:09,256 epoch 5 - iter 1008/1445 - loss 0.04015816 - time (sec): 74.07 - samples/sec: 1667.89 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 22:03:19,744 epoch 5 - iter 1152/1445 - loss 0.03895989 - time (sec): 84.56 - samples/sec: 1672.97 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 22:03:30,067 epoch 5 - iter 1296/1445 - loss 0.03887108 - time (sec): 94.89 - samples/sec: 1664.78 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 22:03:40,569 epoch 5 - iter 1440/1445 - loss 0.03840375 - time (sec): 105.39 - samples/sec: 1664.80 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 22:03:40,994 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:03:40,995 EPOCH 5 done: loss 0.0384 - lr: 0.000017
+2023-10-24 22:03:44,691 DEV : loss 0.133424773812294 - f1-score (micro avg)  0.8276
+2023-10-24 22:03:44,702 saving best model
+2023-10-24 22:03:45,401 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:03:55,990 epoch 6 - iter 144/1445 - loss 0.01932972 - time (sec): 10.59 - samples/sec: 1618.75 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 22:04:06,468 epoch 6 - iter 288/1445 - loss 0.02346905 - time (sec): 21.07 - samples/sec: 1631.06 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 22:04:17,422 epoch 6 - iter 432/1445 - loss 0.02853611 - time (sec): 32.02 - samples/sec: 1665.15 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 22:04:27,879 epoch 6 - iter 576/1445 - loss 0.02850934 - time (sec): 42.48 - samples/sec: 1652.38 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 22:04:38,329 epoch 6 - iter 720/1445 - loss 0.02770765 - time (sec): 52.93 - samples/sec: 1650.35 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 22:04:48,976 epoch 6 - iter 864/1445 - loss 0.02850972 - time (sec): 63.57 - samples/sec: 1656.23 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 22:04:59,427 epoch 6 - iter 1008/1445 - loss 0.02784045 - time (sec): 74.02 - samples/sec: 1666.26 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 22:05:09,931 epoch 6 - iter 1152/1445 - loss 0.02748521 - time (sec): 84.53 - samples/sec: 1666.18 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 22:05:20,372 epoch 6 - iter 1296/1445 - loss 0.02764222 - time (sec): 94.97 - samples/sec: 1669.46 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 22:05:30,719 epoch 6 - iter 1440/1445 - loss 0.02849307 - time (sec): 105.32 - samples/sec: 1668.04 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 22:05:31,053 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:05:31,054 EPOCH 6 done: loss 0.0284 - lr: 0.000013
+2023-10-24 22:05:34,476 DEV : loss 0.1365528404712677 - f1-score (micro avg)  0.8267
+2023-10-24 22:05:34,487 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:05:44,971 epoch 7 - iter 144/1445 - loss 0.01391007 - time (sec): 10.48 - samples/sec: 1706.87 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 22:05:55,671 epoch 7 - iter 288/1445 - loss 0.01968379 - time (sec): 21.18 - samples/sec: 1669.56 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 22:06:06,319 epoch 7 - iter 432/1445 - loss 0.01910457 - time (sec): 31.83 - samples/sec: 1653.60 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 22:06:16,913 epoch 7 - iter 576/1445 - loss 0.02249157 - time (sec): 42.43 - samples/sec: 1670.82 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 22:06:27,746 epoch 7 - iter 720/1445 - loss 0.02204607 - time (sec): 53.26 - samples/sec: 1673.30 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 22:06:38,023 epoch 7 - iter 864/1445 - loss 0.02216207 - time (sec): 63.53 - samples/sec: 1658.27 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 22:06:48,444 epoch 7 - iter 1008/1445 - loss 0.02155640 - time (sec): 73.96 - samples/sec: 1654.13 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 22:06:58,974 epoch 7 - iter 1152/1445 - loss 0.02155786 - time (sec): 84.49 - samples/sec: 1655.26 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 22:07:09,670 epoch 7 - iter 1296/1445 - loss 0.02076335 - time (sec): 95.18 - samples/sec: 1660.34 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 22:07:20,216 epoch 7 - iter 1440/1445 - loss 0.02036066 - time (sec): 105.73 - samples/sec: 1660.35 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 22:07:20,622 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:07:20,623 EPOCH 7 done: loss 0.0204 - lr: 0.000010
+2023-10-24 22:07:24,044 DEV : loss 0.1544482260942459 - f1-score (micro avg)  0.8467
+2023-10-24 22:07:24,056 saving best model
+2023-10-24 22:07:24,752 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:07:35,303 epoch 8 - iter 144/1445 - loss 0.00603330 - time (sec): 10.55 - samples/sec: 1672.68 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 22:07:46,131 epoch 8 - iter 288/1445 - loss 0.01060664 - time (sec): 21.38 - samples/sec: 1658.98 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 22:07:56,453 epoch 8 - iter 432/1445 - loss 0.01037218 - time (sec): 31.70 - samples/sec: 1674.02 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 22:08:07,689 epoch 8 - iter 576/1445 - loss 0.01144562 - time (sec): 42.94 - samples/sec: 1704.63 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 22:08:18,129 epoch 8 - iter 720/1445 - loss 0.01120662 - time (sec): 53.38 - samples/sec: 1689.53 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 22:08:28,593 epoch 8 - iter 864/1445 - loss 0.01145175 - time (sec): 63.84 - samples/sec: 1687.16 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 22:08:39,169 epoch 8 - iter 1008/1445 - loss 0.01216960 - time (sec): 74.42 - samples/sec: 1680.24 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 22:08:49,133 epoch 8 - iter 1152/1445 - loss 0.01273434 - time (sec): 84.38 - samples/sec: 1661.94 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 22:08:59,424 epoch 8 - iter 1296/1445 - loss 0.01238139 - time (sec): 94.67 - samples/sec: 1660.14 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 22:09:10,169 epoch 8 - iter 1440/1445 - loss 0.01332204 - time (sec): 105.42 - samples/sec: 1664.86 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 22:09:10,600 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:09:10,600 EPOCH 8 done: loss 0.0133 - lr: 0.000007
+2023-10-24 22:09:14,309 DEV : loss 0.17273983359336853 - f1-score (micro avg)  0.821
+2023-10-24 22:09:14,320 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:09:25,157 epoch 9 - iter 144/1445 - loss 0.00588071 - time (sec): 10.84 - samples/sec: 1729.19 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 22:09:35,274 epoch 9 - iter 288/1445 - loss 0.00736073 - time (sec): 20.95 - samples/sec: 1673.31 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 22:09:46,262 epoch 9 - iter 432/1445 - loss 0.00797289 - time (sec): 31.94 - samples/sec: 1676.64 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 22:09:56,805 epoch 9 - iter 576/1445 - loss 0.01074603 - time (sec): 42.48 - samples/sec: 1671.91 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 22:10:07,293 epoch 9 - iter 720/1445 - loss 0.01010368 - time (sec): 52.97 - samples/sec: 1667.34 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 22:10:17,826 epoch 9 - iter 864/1445 - loss 0.00940377 - time (sec): 63.50 - samples/sec: 1671.76 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 22:10:28,471 epoch 9 - iter 1008/1445 - loss 0.00943012 - time (sec): 74.15 - samples/sec: 1671.65 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 22:10:38,826 epoch 9 - iter 1152/1445 - loss 0.00936929 - time (sec): 84.51 - samples/sec: 1669.72 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 22:10:49,280 epoch 9 - iter 1296/1445 - loss 0.00923211 - time (sec): 94.96 - samples/sec: 1668.88 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 22:10:59,885 epoch 9 - iter 1440/1445 - loss 0.00932590 - time (sec): 105.56 - samples/sec: 1665.64 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 22:11:00,186 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:11:00,186 EPOCH 9 done: loss 0.0093 - lr: 0.000003
+2023-10-24 22:11:03,616 DEV : loss 0.18522778153419495 - f1-score (micro avg)  0.8267
+2023-10-24 22:11:03,628 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:11:14,197 epoch 10 - iter 144/1445 - loss 0.00628755 - time (sec): 10.57 - samples/sec: 1651.50 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 22:11:24,926 epoch 10 - iter 288/1445 - loss 0.00707012 - time (sec): 21.30 - samples/sec: 1667.33 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 22:11:35,710 epoch 10 - iter 432/1445 - loss 0.00618521 - time (sec): 32.08 - samples/sec: 1697.14 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 22:11:46,638 epoch 10 - iter 576/1445 - loss 0.00651463 - time (sec): 43.01 - samples/sec: 1692.68 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 22:11:56,990 epoch 10 - iter 720/1445 - loss 0.00589889 - time (sec): 53.36 - samples/sec: 1678.07 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 22:12:07,571 epoch 10 - iter 864/1445 - loss 0.00603718 - time (sec): 63.94 - samples/sec: 1669.95 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 22:12:18,192 epoch 10 - iter 1008/1445 - loss 0.00651159 - time (sec): 74.56 - samples/sec: 1664.75 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 22:12:28,603 epoch 10 - iter 1152/1445 - loss 0.00639162 - time (sec): 84.97 - samples/sec: 1665.64 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 22:12:39,228 epoch 10 - iter 1296/1445 - loss 0.00623833 - time (sec): 95.60 - samples/sec: 1659.76 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 22:12:49,561 epoch 10 - iter 1440/1445 - loss 0.00626178 - time (sec): 105.93 - samples/sec: 1659.74 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 22:12:49,857 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:12:49,858 EPOCH 10 done: loss 0.0062 - lr: 0.000000
+2023-10-24 22:12:53,288 DEV : loss 0.18949156999588013 - f1-score (micro avg)  0.831
+2023-10-24 22:12:53,858 ----------------------------------------------------------------------------------------------------
+2023-10-24 22:12:53,859 Loading model from best epoch ...
+2023-10-24 22:12:55,820 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 22:12:59,365 
+Results:
+- F-score (micro) 0.7981
+- F-score (macro) 0.676
+- Accuracy 0.6764
+
+By class:
+              precision    recall  f1-score   support
+
+         PER     0.8382    0.7739    0.8047       482
+         LOC     0.9044    0.8057    0.8522       458
+         ORG     0.4182    0.3333    0.3710        69
+
+   micro avg     0.8425    0.7582    0.7981      1009
+   macro avg     0.7203    0.6376    0.6760      1009
+weighted avg     0.8395    0.7582    0.7966      1009
+
+2023-10-24 22:12:59,365 ----------------------------------------------------------------------------------------------------