Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,506 @@
+2023-10-24 23:21:40,285 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,286 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 23:21:40,286 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,286 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 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 Train:  5777 sentences
+2023-10-24 23:21:40,287         (train_with_dev=False, train_with_test=False)
+2023-10-24 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 Training Params:
+2023-10-24 23:21:40,287  - learning_rate: "5e-05" 
+2023-10-24 23:21:40,287  - mini_batch_size: "4"
+2023-10-24 23:21:40,287  - max_epochs: "10"
+2023-10-24 23:21:40,287  - shuffle: "True"
+2023-10-24 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 Plugins:
+2023-10-24 23:21:40,287  - TensorboardLogger
+2023-10-24 23:21:40,287  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-24 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 Final evaluation on model from best epoch (best-model.pt)
+2023-10-24 23:21:40,287  - metric: "('micro avg', 'f1-score')"
+2023-10-24 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 Computation:
+2023-10-24 23:21:40,287  - compute on device: cuda:0
+2023-10-24 23:21:40,287  - embedding storage: none
+2023-10-24 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
+2023-10-24 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:21:40,287 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-24 23:21:50,481 epoch 1 - iter 144/1445 - loss 1.25687448 - time (sec): 10.19 - samples/sec: 1654.23 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 23:22:00,854 epoch 1 - iter 288/1445 - loss 0.74150684 - time (sec): 20.57 - samples/sec: 1652.68 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 23:22:11,799 epoch 1 - iter 432/1445 - loss 0.55051956 - time (sec): 31.51 - samples/sec: 1686.01 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 23:22:22,479 epoch 1 - iter 576/1445 - loss 0.45307796 - time (sec): 42.19 - samples/sec: 1680.61 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 23:22:33,064 epoch 1 - iter 720/1445 - loss 0.39513176 - time (sec): 52.78 - samples/sec: 1679.07 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 23:22:43,519 epoch 1 - iter 864/1445 - loss 0.35898856 - time (sec): 63.23 - samples/sec: 1670.38 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 23:22:54,299 epoch 1 - iter 1008/1445 - loss 0.32689338 - time (sec): 74.01 - samples/sec: 1679.95 - lr: 0.000035 - momentum: 0.000000
+2023-10-24 23:23:04,536 epoch 1 - iter 1152/1445 - loss 0.30459934 - time (sec): 84.25 - samples/sec: 1675.60 - lr: 0.000040 - momentum: 0.000000
+2023-10-24 23:23:14,906 epoch 1 - iter 1296/1445 - loss 0.28615854 - time (sec): 94.62 - samples/sec: 1674.07 - lr: 0.000045 - momentum: 0.000000
+2023-10-24 23:23:25,291 epoch 1 - iter 1440/1445 - loss 0.26993534 - time (sec): 105.00 - samples/sec: 1673.08 - lr: 0.000050 - momentum: 0.000000
+2023-10-24 23:23:25,621 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:23:25,621 EPOCH 1 done: loss 0.2693 - lr: 0.000050
+2023-10-24 23:23:28,916 DEV : loss 0.13464847207069397 - f1-score (micro avg)  0.4989
+2023-10-24 23:23:28,928 saving best model
+2023-10-24 23:23:29,405 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:23:39,846 epoch 2 - iter 144/1445 - loss 0.11663024 - time (sec): 10.44 - samples/sec: 1666.93 - lr: 0.000049 - momentum: 0.000000
+2023-10-24 23:23:50,257 epoch 2 - iter 288/1445 - loss 0.11374738 - time (sec): 20.85 - samples/sec: 1623.79 - lr: 0.000049 - momentum: 0.000000
+2023-10-24 23:24:01,219 epoch 2 - iter 432/1445 - loss 0.11436629 - time (sec): 31.81 - samples/sec: 1681.21 - lr: 0.000048 - momentum: 0.000000
+2023-10-24 23:24:12,002 epoch 2 - iter 576/1445 - loss 0.10968049 - time (sec): 42.60 - samples/sec: 1680.12 - lr: 0.000048 - momentum: 0.000000
+2023-10-24 23:24:22,453 epoch 2 - iter 720/1445 - loss 0.11276602 - time (sec): 53.05 - samples/sec: 1675.23 - lr: 0.000047 - momentum: 0.000000
+2023-10-24 23:24:32,693 epoch 2 - iter 864/1445 - loss 0.12224799 - time (sec): 63.29 - samples/sec: 1663.20 - lr: 0.000047 - momentum: 0.000000
+2023-10-24 23:24:43,046 epoch 2 - iter 1008/1445 - loss 0.12806467 - time (sec): 73.64 - samples/sec: 1657.02 - lr: 0.000046 - momentum: 0.000000
+2023-10-24 23:24:53,742 epoch 2 - iter 1152/1445 - loss 0.12619685 - time (sec): 84.34 - samples/sec: 1664.66 - lr: 0.000046 - momentum: 0.000000
+2023-10-24 23:25:04,256 epoch 2 - iter 1296/1445 - loss 0.12638505 - time (sec): 94.85 - samples/sec: 1663.82 - lr: 0.000045 - momentum: 0.000000
+2023-10-24 23:25:14,881 epoch 2 - iter 1440/1445 - loss 0.12835770 - time (sec): 105.48 - samples/sec: 1666.64 - lr: 0.000044 - momentum: 0.000000
+2023-10-24 23:25:15,196 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:25:15,197 EPOCH 2 done: loss 0.1283 - lr: 0.000044
+2023-10-24 23:25:18,912 DEV : loss 0.14913305640220642 - f1-score (micro avg)  0.5666
+2023-10-24 23:25:18,924 saving best model
+2023-10-24 23:25:19,520 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:25:30,192 epoch 3 - iter 144/1445 - loss 0.09556737 - time (sec): 10.67 - samples/sec: 1676.80 - lr: 0.000044 - momentum: 0.000000
+2023-10-24 23:25:40,576 epoch 3 - iter 288/1445 - loss 0.09151055 - time (sec): 21.06 - samples/sec: 1686.19 - lr: 0.000043 - momentum: 0.000000
+2023-10-24 23:25:51,424 epoch 3 - iter 432/1445 - loss 0.09590453 - time (sec): 31.90 - samples/sec: 1698.93 - lr: 0.000043 - momentum: 0.000000
+2023-10-24 23:26:02,002 epoch 3 - iter 576/1445 - loss 0.09325284 - time (sec): 42.48 - samples/sec: 1699.52 - lr: 0.000042 - momentum: 0.000000
+2023-10-24 23:26:12,235 epoch 3 - iter 720/1445 - loss 0.09294158 - time (sec): 52.71 - samples/sec: 1690.27 - lr: 0.000042 - momentum: 0.000000
+2023-10-24 23:26:22,689 epoch 3 - iter 864/1445 - loss 0.09217848 - time (sec): 63.17 - samples/sec: 1678.39 - lr: 0.000041 - momentum: 0.000000
+2023-10-24 23:26:32,980 epoch 3 - iter 1008/1445 - loss 0.09182787 - time (sec): 73.46 - samples/sec: 1668.27 - lr: 0.000041 - momentum: 0.000000
+2023-10-24 23:26:43,805 epoch 3 - iter 1152/1445 - loss 0.09081107 - time (sec): 84.28 - samples/sec: 1665.95 - lr: 0.000040 - momentum: 0.000000
+2023-10-24 23:26:54,149 epoch 3 - iter 1296/1445 - loss 0.08982439 - time (sec): 94.63 - samples/sec: 1666.10 - lr: 0.000039 - momentum: 0.000000
+2023-10-24 23:27:04,923 epoch 3 - iter 1440/1445 - loss 0.08774452 - time (sec): 105.40 - samples/sec: 1666.91 - lr: 0.000039 - momentum: 0.000000
+2023-10-24 23:27:05,285 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:27:05,286 EPOCH 3 done: loss 0.0876 - lr: 0.000039
+2023-10-24 23:27:08,720 DEV : loss 0.09554920345544815 - f1-score (micro avg)  0.7987
+2023-10-24 23:27:08,732 saving best model
+2023-10-24 23:27:09,323 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:27:19,724 epoch 4 - iter 144/1445 - loss 0.05617425 - time (sec): 10.40 - samples/sec: 1681.39 - lr: 0.000038 - momentum: 0.000000
+2023-10-24 23:27:30,780 epoch 4 - iter 288/1445 - loss 0.05608470 - time (sec): 21.46 - samples/sec: 1634.93 - lr: 0.000038 - momentum: 0.000000
+2023-10-24 23:27:41,462 epoch 4 - iter 432/1445 - loss 0.05672814 - time (sec): 32.14 - samples/sec: 1662.75 - lr: 0.000037 - momentum: 0.000000
+2023-10-24 23:27:52,225 epoch 4 - iter 576/1445 - loss 0.05849627 - time (sec): 42.90 - samples/sec: 1671.54 - lr: 0.000037 - momentum: 0.000000
+2023-10-24 23:28:02,934 epoch 4 - iter 720/1445 - loss 0.05648828 - time (sec): 53.61 - samples/sec: 1672.20 - lr: 0.000036 - momentum: 0.000000
+2023-10-24 23:28:13,606 epoch 4 - iter 864/1445 - loss 0.05791966 - time (sec): 64.28 - samples/sec: 1674.82 - lr: 0.000036 - momentum: 0.000000
+2023-10-24 23:28:23,554 epoch 4 - iter 1008/1445 - loss 0.05982341 - time (sec): 74.23 - samples/sec: 1665.23 - lr: 0.000035 - momentum: 0.000000
+2023-10-24 23:28:33,833 epoch 4 - iter 1152/1445 - loss 0.06036417 - time (sec): 84.51 - samples/sec: 1661.07 - lr: 0.000034 - momentum: 0.000000
+2023-10-24 23:28:44,524 epoch 4 - iter 1296/1445 - loss 0.06076328 - time (sec): 95.20 - samples/sec: 1659.37 - lr: 0.000034 - momentum: 0.000000
+2023-10-24 23:28:55,064 epoch 4 - iter 1440/1445 - loss 0.06071194 - time (sec): 105.74 - samples/sec: 1662.20 - lr: 0.000033 - momentum: 0.000000
+2023-10-24 23:28:55,379 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:28:55,379 EPOCH 4 done: loss 0.0607 - lr: 0.000033
+2023-10-24 23:28:58,805 DEV : loss 0.14087821543216705 - f1-score (micro avg)  0.7709
+2023-10-24 23:28:58,817 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:29:09,059 epoch 5 - iter 144/1445 - loss 0.03779963 - time (sec): 10.24 - samples/sec: 1583.68 - lr: 0.000033 - momentum: 0.000000
+2023-10-24 23:29:19,818 epoch 5 - iter 288/1445 - loss 0.05292038 - time (sec): 21.00 - samples/sec: 1627.18 - lr: 0.000032 - momentum: 0.000000
+2023-10-24 23:29:29,864 epoch 5 - iter 432/1445 - loss 0.04769913 - time (sec): 31.05 - samples/sec: 1618.22 - lr: 0.000032 - momentum: 0.000000
+2023-10-24 23:29:40,463 epoch 5 - iter 576/1445 - loss 0.04620324 - time (sec): 41.65 - samples/sec: 1625.30 - lr: 0.000031 - momentum: 0.000000
+2023-10-24 23:29:51,150 epoch 5 - iter 720/1445 - loss 0.04549958 - time (sec): 52.33 - samples/sec: 1637.80 - lr: 0.000031 - momentum: 0.000000
+2023-10-24 23:30:01,787 epoch 5 - iter 864/1445 - loss 0.04525116 - time (sec): 62.97 - samples/sec: 1646.50 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 23:30:12,838 epoch 5 - iter 1008/1445 - loss 0.04663334 - time (sec): 74.02 - samples/sec: 1653.57 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 23:30:23,025 epoch 5 - iter 1152/1445 - loss 0.04587806 - time (sec): 84.21 - samples/sec: 1652.03 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 23:30:33,618 epoch 5 - iter 1296/1445 - loss 0.04699800 - time (sec): 94.80 - samples/sec: 1656.41 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 23:30:44,514 epoch 5 - iter 1440/1445 - loss 0.04628123 - time (sec): 105.70 - samples/sec: 1663.62 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 23:30:44,822 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:30:44,823 EPOCH 5 done: loss 0.0463 - lr: 0.000028
+2023-10-24 23:30:48,549 DEV : loss 0.19031141698360443 - f1-score (micro avg)  0.7835
+2023-10-24 23:30:48,561 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:30:59,126 epoch 6 - iter 144/1445 - loss 0.03075064 - time (sec): 10.56 - samples/sec: 1638.27 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 23:31:09,574 epoch 6 - iter 288/1445 - loss 0.02796459 - time (sec): 21.01 - samples/sec: 1663.44 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 23:31:19,916 epoch 6 - iter 432/1445 - loss 0.02789741 - time (sec): 31.35 - samples/sec: 1657.60 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 23:31:30,428 epoch 6 - iter 576/1445 - loss 0.02733910 - time (sec): 41.87 - samples/sec: 1666.41 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 23:31:41,324 epoch 6 - iter 720/1445 - loss 0.02846954 - time (sec): 52.76 - samples/sec: 1676.89 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 23:31:51,905 epoch 6 - iter 864/1445 - loss 0.03196300 - time (sec): 63.34 - samples/sec: 1676.82 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 23:32:02,373 epoch 6 - iter 1008/1445 - loss 0.03158090 - time (sec): 73.81 - samples/sec: 1678.18 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 23:32:12,706 epoch 6 - iter 1152/1445 - loss 0.03159776 - time (sec): 84.14 - samples/sec: 1669.57 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 23:32:23,320 epoch 6 - iter 1296/1445 - loss 0.03120304 - time (sec): 94.76 - samples/sec: 1669.75 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 23:32:33,943 epoch 6 - iter 1440/1445 - loss 0.03155238 - time (sec): 105.38 - samples/sec: 1662.26 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 23:32:34,425 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:32:34,426 EPOCH 6 done: loss 0.0314 - lr: 0.000022
+2023-10-24 23:32:37,842 DEV : loss 0.2146977335214615 - f1-score (micro avg)  0.766
+2023-10-24 23:32:37,854 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:32:48,058 epoch 7 - iter 144/1445 - loss 0.02441531 - time (sec): 10.20 - samples/sec: 1624.67 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 23:32:58,154 epoch 7 - iter 288/1445 - loss 0.01969335 - time (sec): 20.30 - samples/sec: 1604.97 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 23:33:09,274 epoch 7 - iter 432/1445 - loss 0.02274451 - time (sec): 31.42 - samples/sec: 1645.46 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 23:33:19,975 epoch 7 - iter 576/1445 - loss 0.02260029 - time (sec): 42.12 - samples/sec: 1633.49 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 23:33:30,556 epoch 7 - iter 720/1445 - loss 0.02066555 - time (sec): 52.70 - samples/sec: 1653.84 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 23:33:41,236 epoch 7 - iter 864/1445 - loss 0.02077775 - time (sec): 63.38 - samples/sec: 1654.21 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 23:33:51,553 epoch 7 - iter 1008/1445 - loss 0.02058252 - time (sec): 73.70 - samples/sec: 1646.87 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 23:34:02,072 epoch 7 - iter 1152/1445 - loss 0.02160228 - time (sec): 84.22 - samples/sec: 1648.44 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 23:34:12,751 epoch 7 - iter 1296/1445 - loss 0.02180055 - time (sec): 94.90 - samples/sec: 1651.68 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 23:34:23,741 epoch 7 - iter 1440/1445 - loss 0.02146058 - time (sec): 105.89 - samples/sec: 1660.10 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 23:34:24,083 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:34:24,083 EPOCH 7 done: loss 0.0215 - lr: 0.000017
+2023-10-24 23:34:27,511 DEV : loss 0.18124361336231232 - f1-score (micro avg)  0.7818
+2023-10-24 23:34:27,523 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:34:37,876 epoch 8 - iter 144/1445 - loss 0.01881265 - time (sec): 10.35 - samples/sec: 1675.43 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 23:34:48,384 epoch 8 - iter 288/1445 - loss 0.02283118 - time (sec): 20.86 - samples/sec: 1668.74 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 23:34:58,579 epoch 8 - iter 432/1445 - loss 0.02220532 - time (sec): 31.05 - samples/sec: 1643.19 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 23:35:09,315 epoch 8 - iter 576/1445 - loss 0.01976420 - time (sec): 41.79 - samples/sec: 1664.66 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 23:35:19,753 epoch 8 - iter 720/1445 - loss 0.01917837 - time (sec): 52.23 - samples/sec: 1659.44 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 23:35:30,497 epoch 8 - iter 864/1445 - loss 0.01842880 - time (sec): 62.97 - samples/sec: 1652.58 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 23:35:41,106 epoch 8 - iter 1008/1445 - loss 0.01678623 - time (sec): 73.58 - samples/sec: 1656.73 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 23:35:51,530 epoch 8 - iter 1152/1445 - loss 0.01618883 - time (sec): 84.01 - samples/sec: 1653.43 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 23:36:02,329 epoch 8 - iter 1296/1445 - loss 0.01598200 - time (sec): 94.81 - samples/sec: 1656.02 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 23:36:13,079 epoch 8 - iter 1440/1445 - loss 0.01527453 - time (sec): 105.55 - samples/sec: 1661.63 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 23:36:13,481 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:36:13,481 EPOCH 8 done: loss 0.0153 - lr: 0.000011
+2023-10-24 23:36:17,208 DEV : loss 0.19522705674171448 - f1-score (micro avg)  0.8037
+2023-10-24 23:36:17,220 saving best model
+2023-10-24 23:36:17,807 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:36:28,281 epoch 9 - iter 144/1445 - loss 0.00487168 - time (sec): 10.47 - samples/sec: 1668.77 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 23:36:38,986 epoch 9 - iter 288/1445 - loss 0.00375882 - time (sec): 21.18 - samples/sec: 1659.68 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 23:36:49,311 epoch 9 - iter 432/1445 - loss 0.00501835 - time (sec): 31.50 - samples/sec: 1662.22 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 23:36:59,963 epoch 9 - iter 576/1445 - loss 0.00620410 - time (sec): 42.16 - samples/sec: 1674.46 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 23:37:10,341 epoch 9 - iter 720/1445 - loss 0.00619216 - time (sec): 52.53 - samples/sec: 1673.29 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 23:37:21,076 epoch 9 - iter 864/1445 - loss 0.00765207 - time (sec): 63.27 - samples/sec: 1670.95 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 23:37:31,604 epoch 9 - iter 1008/1445 - loss 0.00810858 - time (sec): 73.80 - samples/sec: 1674.78 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 23:37:42,611 epoch 9 - iter 1152/1445 - loss 0.00861122 - time (sec): 84.80 - samples/sec: 1674.31 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 23:37:52,574 epoch 9 - iter 1296/1445 - loss 0.00885029 - time (sec): 94.77 - samples/sec: 1668.72 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 23:38:03,199 epoch 9 - iter 1440/1445 - loss 0.00850372 - time (sec): 105.39 - samples/sec: 1667.11 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 23:38:03,529 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:38:03,530 EPOCH 9 done: loss 0.0085 - lr: 0.000006
+2023-10-24 23:38:06,954 DEV : loss 0.21074502170085907 - f1-score (micro avg)  0.8142
+2023-10-24 23:38:06,966 saving best model
+2023-10-24 23:38:07,559 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:38:18,127 epoch 10 - iter 144/1445 - loss 0.00645055 - time (sec): 10.57 - samples/sec: 1631.27 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 23:38:28,580 epoch 10 - iter 288/1445 - loss 0.00490595 - time (sec): 21.02 - samples/sec: 1663.02 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 23:38:39,577 epoch 10 - iter 432/1445 - loss 0.00556624 - time (sec): 32.02 - samples/sec: 1654.94 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 23:38:50,128 epoch 10 - iter 576/1445 - loss 0.00492256 - time (sec): 42.57 - samples/sec: 1664.16 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 23:39:00,748 epoch 10 - iter 720/1445 - loss 0.00507698 - time (sec): 53.19 - samples/sec: 1666.96 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 23:39:11,086 epoch 10 - iter 864/1445 - loss 0.00484983 - time (sec): 63.53 - samples/sec: 1664.20 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 23:39:21,382 epoch 10 - iter 1008/1445 - loss 0.00494508 - time (sec): 73.82 - samples/sec: 1664.17 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 23:39:32,014 epoch 10 - iter 1152/1445 - loss 0.00513985 - time (sec): 84.45 - samples/sec: 1662.77 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 23:39:42,971 epoch 10 - iter 1296/1445 - loss 0.00514301 - time (sec): 95.41 - samples/sec: 1668.08 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 23:39:53,162 epoch 10 - iter 1440/1445 - loss 0.00522215 - time (sec): 105.60 - samples/sec: 1664.03 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 23:39:53,489 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:39:53,489 EPOCH 10 done: loss 0.0053 - lr: 0.000000
+2023-10-24 23:39:56,913 DEV : loss 0.21832986176013947 - f1-score (micro avg)  0.8061
+2023-10-24 23:39:57,402 ----------------------------------------------------------------------------------------------------
+2023-10-24 23:39:57,403 Loading model from best epoch ...
+2023-10-24 23:39:59,204 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 23:40:02,743 
+Results:
+- F-score (micro) 0.7996
+- F-score (macro) 0.694
+- Accuracy 0.6756
+
+By class:
+              precision    recall  f1-score   support
+
+         PER     0.8510    0.7822    0.8151       482
+         LOC     0.9008    0.7729    0.8320       458
+         ORG     0.5435    0.3623    0.4348        69
+
+   micro avg     0.8571    0.7493    0.7996      1009
+   macro avg     0.7651    0.6391    0.6940      1009
+weighted avg     0.8526    0.7493    0.7968      1009
+
+2023-10-24 23:40:02,743 ----------------------------------------------------------------------------------------------------