Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,506 @@
+2023-10-25 03:21:07,036 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,036 Model: "SequenceTagger(
+  (embeddings): TransformerWordEmbeddings(
+    (model): BertModel(
+      (embeddings): BertEmbeddings(
+        (word_embeddings): Embedding(64001, 768)
+        (position_embeddings): Embedding(512, 768)
+        (token_type_embeddings): Embedding(2, 768)
+        (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+        (dropout): Dropout(p=0.1, inplace=False)
+      )
+      (encoder): BertEncoder(
+        (layer): ModuleList(
+          (0): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (1): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (2): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (3): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (4): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (5): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (6): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (7): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (8): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (9): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (10): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (11): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+        )
+      )
+      (pooler): BertPooler(
+        (dense): Linear(in_features=768, out_features=768, bias=True)
+        (activation): Tanh()
+      )
+    )
+  )
+  (locked_dropout): LockedDropout(p=0.5)
+  (linear): Linear(in_features=768, out_features=13, bias=True)
+  (loss_function): CrossEntropyLoss()
+)"
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,037 MultiCorpus: 5777 train + 722 dev + 723 test sentences
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/nl
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,037 Train:  5777 sentences
+2023-10-25 03:21:07,037         (train_with_dev=False, train_with_test=False)
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,037 Training Params:
+2023-10-25 03:21:07,037  - learning_rate: "5e-05" 
+2023-10-25 03:21:07,037  - mini_batch_size: "8"
+2023-10-25 03:21:07,037  - max_epochs: "10"
+2023-10-25 03:21:07,037  - shuffle: "True"
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,037 Plugins:
+2023-10-25 03:21:07,037  - TensorboardLogger
+2023-10-25 03:21:07,037  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,037 Final evaluation on model from best epoch (best-model.pt)
+2023-10-25 03:21:07,037  - metric: "('micro avg', 'f1-score')"
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,037 Computation:
+2023-10-25 03:21:07,037  - compute on device: cuda:0
+2023-10-25 03:21:07,037  - embedding storage: none
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,037 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
+2023-10-25 03:21:07,037 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,038 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:21:07,038 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-25 03:21:15,767 epoch 1 - iter 72/723 - loss 1.68766467 - time (sec): 8.73 - samples/sec: 1919.80 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 03:21:23,724 epoch 1 - iter 144/723 - loss 0.99031859 - time (sec): 16.69 - samples/sec: 1975.15 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 03:21:32,094 epoch 1 - iter 216/723 - loss 0.71808221 - time (sec): 25.06 - samples/sec: 2003.67 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 03:21:40,978 epoch 1 - iter 288/723 - loss 0.57309784 - time (sec): 33.94 - samples/sec: 2017.52 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 03:21:49,174 epoch 1 - iter 360/723 - loss 0.49129012 - time (sec): 42.14 - samples/sec: 2020.68 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 03:21:57,936 epoch 1 - iter 432/723 - loss 0.43005413 - time (sec): 50.90 - samples/sec: 2038.58 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 03:22:06,610 epoch 1 - iter 504/723 - loss 0.38879308 - time (sec): 59.57 - samples/sec: 2042.37 - lr: 0.000035 - momentum: 0.000000
+2023-10-25 03:22:15,073 epoch 1 - iter 576/723 - loss 0.35796702 - time (sec): 68.03 - samples/sec: 2041.20 - lr: 0.000040 - momentum: 0.000000
+2023-10-25 03:22:24,126 epoch 1 - iter 648/723 - loss 0.33078723 - time (sec): 77.09 - samples/sec: 2042.41 - lr: 0.000045 - momentum: 0.000000
+2023-10-25 03:22:33,094 epoch 1 - iter 720/723 - loss 0.31081390 - time (sec): 86.06 - samples/sec: 2040.23 - lr: 0.000050 - momentum: 0.000000
+2023-10-25 03:22:33,419 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:22:33,420 EPOCH 1 done: loss 0.3102 - lr: 0.000050
+2023-10-25 03:22:36,444 DEV : loss 0.10029962658882141 - f1-score (micro avg)  0.714
+2023-10-25 03:22:36,455 saving best model
+2023-10-25 03:22:36,922 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:22:45,659 epoch 2 - iter 72/723 - loss 0.12090345 - time (sec): 8.74 - samples/sec: 1958.50 - lr: 0.000049 - momentum: 0.000000
+2023-10-25 03:22:53,891 epoch 2 - iter 144/723 - loss 0.11010184 - time (sec): 16.97 - samples/sec: 2023.18 - lr: 0.000049 - momentum: 0.000000
+2023-10-25 03:23:02,247 epoch 2 - iter 216/723 - loss 0.10565874 - time (sec): 25.32 - samples/sec: 2041.71 - lr: 0.000048 - momentum: 0.000000
+2023-10-25 03:23:10,874 epoch 2 - iter 288/723 - loss 0.10233445 - time (sec): 33.95 - samples/sec: 2038.73 - lr: 0.000048 - momentum: 0.000000
+2023-10-25 03:23:19,521 epoch 2 - iter 360/723 - loss 0.09988170 - time (sec): 42.60 - samples/sec: 2031.02 - lr: 0.000047 - momentum: 0.000000
+2023-10-25 03:23:28,031 epoch 2 - iter 432/723 - loss 0.09714710 - time (sec): 51.11 - samples/sec: 2031.30 - lr: 0.000047 - momentum: 0.000000
+2023-10-25 03:23:36,548 epoch 2 - iter 504/723 - loss 0.09721388 - time (sec): 59.62 - samples/sec: 2030.47 - lr: 0.000046 - momentum: 0.000000
+2023-10-25 03:23:44,959 epoch 2 - iter 576/723 - loss 0.09638112 - time (sec): 68.04 - samples/sec: 2035.31 - lr: 0.000046 - momentum: 0.000000
+2023-10-25 03:23:54,130 epoch 2 - iter 648/723 - loss 0.09712113 - time (sec): 77.21 - samples/sec: 2032.68 - lr: 0.000045 - momentum: 0.000000
+2023-10-25 03:24:03,482 epoch 2 - iter 720/723 - loss 0.09496368 - time (sec): 86.56 - samples/sec: 2029.14 - lr: 0.000044 - momentum: 0.000000
+2023-10-25 03:24:03,845 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:24:03,845 EPOCH 2 done: loss 0.0951 - lr: 0.000044
+2023-10-25 03:24:07,270 DEV : loss 0.08907141536474228 - f1-score (micro avg)  0.7752
+2023-10-25 03:24:07,282 saving best model
+2023-10-25 03:24:07,866 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:24:16,521 epoch 3 - iter 72/723 - loss 0.05697145 - time (sec): 8.65 - samples/sec: 1979.04 - lr: 0.000044 - momentum: 0.000000
+2023-10-25 03:24:25,015 epoch 3 - iter 144/723 - loss 0.06365511 - time (sec): 17.15 - samples/sec: 2016.66 - lr: 0.000043 - momentum: 0.000000
+2023-10-25 03:24:34,291 epoch 3 - iter 216/723 - loss 0.06006955 - time (sec): 26.42 - samples/sec: 2028.12 - lr: 0.000043 - momentum: 0.000000
+2023-10-25 03:24:42,967 epoch 3 - iter 288/723 - loss 0.05978662 - time (sec): 35.10 - samples/sec: 2039.51 - lr: 0.000042 - momentum: 0.000000
+2023-10-25 03:24:51,561 epoch 3 - iter 360/723 - loss 0.06048031 - time (sec): 43.69 - samples/sec: 2052.41 - lr: 0.000042 - momentum: 0.000000
+2023-10-25 03:24:59,876 epoch 3 - iter 432/723 - loss 0.06265153 - time (sec): 52.01 - samples/sec: 2048.22 - lr: 0.000041 - momentum: 0.000000
+2023-10-25 03:25:08,066 epoch 3 - iter 504/723 - loss 0.06140349 - time (sec): 60.20 - samples/sec: 2048.19 - lr: 0.000041 - momentum: 0.000000
+2023-10-25 03:25:16,386 epoch 3 - iter 576/723 - loss 0.06149397 - time (sec): 68.52 - samples/sec: 2052.30 - lr: 0.000040 - momentum: 0.000000
+2023-10-25 03:25:24,635 epoch 3 - iter 648/723 - loss 0.06212052 - time (sec): 76.77 - samples/sec: 2055.82 - lr: 0.000039 - momentum: 0.000000
+2023-10-25 03:25:33,470 epoch 3 - iter 720/723 - loss 0.06192748 - time (sec): 85.60 - samples/sec: 2049.87 - lr: 0.000039 - momentum: 0.000000
+2023-10-25 03:25:33,882 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:25:33,883 EPOCH 3 done: loss 0.0618 - lr: 0.000039
+2023-10-25 03:25:37,591 DEV : loss 0.08058985322713852 - f1-score (micro avg)  0.8289
+2023-10-25 03:25:37,603 saving best model
+2023-10-25 03:25:38,165 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:25:46,598 epoch 4 - iter 72/723 - loss 0.02797752 - time (sec): 8.43 - samples/sec: 1994.47 - lr: 0.000038 - momentum: 0.000000
+2023-10-25 03:25:55,309 epoch 4 - iter 144/723 - loss 0.03614415 - time (sec): 17.14 - samples/sec: 2030.17 - lr: 0.000038 - momentum: 0.000000
+2023-10-25 03:26:04,448 epoch 4 - iter 216/723 - loss 0.04145400 - time (sec): 26.28 - samples/sec: 2028.97 - lr: 0.000037 - momentum: 0.000000
+2023-10-25 03:26:13,754 epoch 4 - iter 288/723 - loss 0.04451492 - time (sec): 35.59 - samples/sec: 1996.38 - lr: 0.000037 - momentum: 0.000000
+2023-10-25 03:26:22,376 epoch 4 - iter 360/723 - loss 0.04603311 - time (sec): 44.21 - samples/sec: 2007.61 - lr: 0.000036 - momentum: 0.000000
+2023-10-25 03:26:30,692 epoch 4 - iter 432/723 - loss 0.04476476 - time (sec): 52.53 - samples/sec: 2006.73 - lr: 0.000036 - momentum: 0.000000
+2023-10-25 03:26:39,615 epoch 4 - iter 504/723 - loss 0.04287179 - time (sec): 61.45 - samples/sec: 2021.07 - lr: 0.000035 - momentum: 0.000000
+2023-10-25 03:26:48,061 epoch 4 - iter 576/723 - loss 0.04179019 - time (sec): 69.89 - samples/sec: 2023.56 - lr: 0.000034 - momentum: 0.000000
+2023-10-25 03:26:55,925 epoch 4 - iter 648/723 - loss 0.04178069 - time (sec): 77.76 - samples/sec: 2029.52 - lr: 0.000034 - momentum: 0.000000
+2023-10-25 03:27:04,356 epoch 4 - iter 720/723 - loss 0.04186433 - time (sec): 86.19 - samples/sec: 2040.59 - lr: 0.000033 - momentum: 0.000000
+2023-10-25 03:27:04,610 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:27:04,610 EPOCH 4 done: loss 0.0419 - lr: 0.000033
+2023-10-25 03:27:08,040 DEV : loss 0.10547219961881638 - f1-score (micro avg)  0.8136
+2023-10-25 03:27:08,051 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:27:16,658 epoch 5 - iter 72/723 - loss 0.03237456 - time (sec): 8.61 - samples/sec: 2057.62 - lr: 0.000033 - momentum: 0.000000
+2023-10-25 03:27:25,600 epoch 5 - iter 144/723 - loss 0.03452148 - time (sec): 17.55 - samples/sec: 2018.99 - lr: 0.000032 - momentum: 0.000000
+2023-10-25 03:27:33,985 epoch 5 - iter 216/723 - loss 0.03349648 - time (sec): 25.93 - samples/sec: 2037.16 - lr: 0.000032 - momentum: 0.000000
+2023-10-25 03:27:42,171 epoch 5 - iter 288/723 - loss 0.03304803 - time (sec): 34.12 - samples/sec: 2027.60 - lr: 0.000031 - momentum: 0.000000
+2023-10-25 03:27:50,434 epoch 5 - iter 360/723 - loss 0.03166254 - time (sec): 42.38 - samples/sec: 2034.44 - lr: 0.000031 - momentum: 0.000000
+2023-10-25 03:27:59,929 epoch 5 - iter 432/723 - loss 0.02996305 - time (sec): 51.88 - samples/sec: 2016.91 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 03:28:08,267 epoch 5 - iter 504/723 - loss 0.03108088 - time (sec): 60.21 - samples/sec: 2017.39 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 03:28:17,112 epoch 5 - iter 576/723 - loss 0.03441065 - time (sec): 69.06 - samples/sec: 2021.48 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 03:28:26,189 epoch 5 - iter 648/723 - loss 0.03309049 - time (sec): 78.14 - samples/sec: 2025.80 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 03:28:34,845 epoch 5 - iter 720/723 - loss 0.03290640 - time (sec): 86.79 - samples/sec: 2025.49 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 03:28:35,078 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:28:35,078 EPOCH 5 done: loss 0.0329 - lr: 0.000028
+2023-10-25 03:28:38,506 DEV : loss 0.10743129253387451 - f1-score (micro avg)  0.8259
+2023-10-25 03:28:38,518 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:28:47,146 epoch 6 - iter 72/723 - loss 0.01950180 - time (sec): 8.63 - samples/sec: 2088.78 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 03:28:54,838 epoch 6 - iter 144/723 - loss 0.02431246 - time (sec): 16.32 - samples/sec: 2088.92 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 03:29:03,341 epoch 6 - iter 216/723 - loss 0.02554660 - time (sec): 24.82 - samples/sec: 2097.06 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 03:29:12,960 epoch 6 - iter 288/723 - loss 0.02489555 - time (sec): 34.44 - samples/sec: 2067.63 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 03:29:21,612 epoch 6 - iter 360/723 - loss 0.02519088 - time (sec): 43.09 - samples/sec: 2065.88 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 03:29:30,520 epoch 6 - iter 432/723 - loss 0.02472334 - time (sec): 52.00 - samples/sec: 2055.69 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 03:29:39,539 epoch 6 - iter 504/723 - loss 0.02448090 - time (sec): 61.02 - samples/sec: 2041.79 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 03:29:47,981 epoch 6 - iter 576/723 - loss 0.02586243 - time (sec): 69.46 - samples/sec: 2041.93 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 03:29:55,961 epoch 6 - iter 648/723 - loss 0.02606734 - time (sec): 77.44 - samples/sec: 2044.90 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 03:30:04,986 epoch 6 - iter 720/723 - loss 0.02562324 - time (sec): 86.47 - samples/sec: 2032.59 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 03:30:05,288 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:30:05,288 EPOCH 6 done: loss 0.0257 - lr: 0.000022
+2023-10-25 03:30:09,014 DEV : loss 0.14865967631340027 - f1-score (micro avg)  0.8278
+2023-10-25 03:30:09,026 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:30:17,847 epoch 7 - iter 72/723 - loss 0.01296776 - time (sec): 8.82 - samples/sec: 2066.52 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 03:30:26,902 epoch 7 - iter 144/723 - loss 0.01515821 - time (sec): 17.87 - samples/sec: 2044.78 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 03:30:35,247 epoch 7 - iter 216/723 - loss 0.01484702 - time (sec): 26.22 - samples/sec: 2036.37 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 03:30:44,046 epoch 7 - iter 288/723 - loss 0.01579797 - time (sec): 35.02 - samples/sec: 2029.75 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 03:30:52,631 epoch 7 - iter 360/723 - loss 0.01628311 - time (sec): 43.60 - samples/sec: 2030.46 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 03:31:01,153 epoch 7 - iter 432/723 - loss 0.01613784 - time (sec): 52.13 - samples/sec: 2033.21 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 03:31:09,837 epoch 7 - iter 504/723 - loss 0.01677860 - time (sec): 60.81 - samples/sec: 2024.48 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 03:31:18,928 epoch 7 - iter 576/723 - loss 0.01663651 - time (sec): 69.90 - samples/sec: 2025.46 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 03:31:27,367 epoch 7 - iter 648/723 - loss 0.01651969 - time (sec): 78.34 - samples/sec: 2028.03 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 03:31:35,458 epoch 7 - iter 720/723 - loss 0.01681181 - time (sec): 86.43 - samples/sec: 2030.51 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 03:31:35,920 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:31:35,920 EPOCH 7 done: loss 0.0168 - lr: 0.000017
+2023-10-25 03:31:39,682 DEV : loss 0.15617409348487854 - f1-score (micro avg)  0.8255
+2023-10-25 03:31:39,694 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:31:48,026 epoch 8 - iter 72/723 - loss 0.01544069 - time (sec): 8.33 - samples/sec: 2031.15 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 03:31:56,092 epoch 8 - iter 144/723 - loss 0.01094618 - time (sec): 16.40 - samples/sec: 2069.54 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 03:32:04,253 epoch 8 - iter 216/723 - loss 0.01140394 - time (sec): 24.56 - samples/sec: 2055.24 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 03:32:12,929 epoch 8 - iter 288/723 - loss 0.01145852 - time (sec): 33.23 - samples/sec: 2030.80 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 03:32:21,548 epoch 8 - iter 360/723 - loss 0.01128244 - time (sec): 41.85 - samples/sec: 2028.57 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 03:32:30,258 epoch 8 - iter 432/723 - loss 0.01132223 - time (sec): 50.56 - samples/sec: 2029.34 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 03:32:39,319 epoch 8 - iter 504/723 - loss 0.01152129 - time (sec): 59.62 - samples/sec: 2012.44 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 03:32:47,863 epoch 8 - iter 576/723 - loss 0.01234181 - time (sec): 68.17 - samples/sec: 2017.87 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 03:32:56,530 epoch 8 - iter 648/723 - loss 0.01271235 - time (sec): 76.83 - samples/sec: 2033.67 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 03:33:06,090 epoch 8 - iter 720/723 - loss 0.01201023 - time (sec): 86.40 - samples/sec: 2032.91 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 03:33:06,338 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:33:06,338 EPOCH 8 done: loss 0.0120 - lr: 0.000011
+2023-10-25 03:33:09,773 DEV : loss 0.17202885448932648 - f1-score (micro avg)  0.8299
+2023-10-25 03:33:09,785 saving best model
+2023-10-25 03:33:10,374 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:33:19,969 epoch 9 - iter 72/723 - loss 0.01007116 - time (sec): 9.59 - samples/sec: 1891.90 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 03:33:28,571 epoch 9 - iter 144/723 - loss 0.01044210 - time (sec): 18.20 - samples/sec: 1982.50 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 03:33:37,499 epoch 9 - iter 216/723 - loss 0.01026889 - time (sec): 27.12 - samples/sec: 2014.27 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 03:33:46,186 epoch 9 - iter 288/723 - loss 0.00973665 - time (sec): 35.81 - samples/sec: 2022.23 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 03:33:54,191 epoch 9 - iter 360/723 - loss 0.00955647 - time (sec): 43.82 - samples/sec: 2027.79 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 03:34:02,428 epoch 9 - iter 432/723 - loss 0.00922189 - time (sec): 52.05 - samples/sec: 2024.17 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 03:34:11,130 epoch 9 - iter 504/723 - loss 0.00851347 - time (sec): 60.76 - samples/sec: 2033.68 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 03:34:19,732 epoch 9 - iter 576/723 - loss 0.00799039 - time (sec): 69.36 - samples/sec: 2034.77 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 03:34:28,576 epoch 9 - iter 648/723 - loss 0.00810368 - time (sec): 78.20 - samples/sec: 2031.04 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 03:34:36,912 epoch 9 - iter 720/723 - loss 0.00785735 - time (sec): 86.54 - samples/sec: 2031.17 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 03:34:37,188 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:34:37,188 EPOCH 9 done: loss 0.0078 - lr: 0.000006
+2023-10-25 03:34:40,919 DEV : loss 0.17869263887405396 - f1-score (micro avg)  0.8368
+2023-10-25 03:34:40,931 saving best model
+2023-10-25 03:34:41,550 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:34:50,569 epoch 10 - iter 72/723 - loss 0.00494847 - time (sec): 9.02 - samples/sec: 1973.49 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 03:34:59,482 epoch 10 - iter 144/723 - loss 0.00333403 - time (sec): 17.93 - samples/sec: 1997.15 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 03:35:07,959 epoch 10 - iter 216/723 - loss 0.00471172 - time (sec): 26.41 - samples/sec: 1988.70 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 03:35:16,347 epoch 10 - iter 288/723 - loss 0.00424818 - time (sec): 34.80 - samples/sec: 1996.50 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 03:35:25,001 epoch 10 - iter 360/723 - loss 0.00450474 - time (sec): 43.45 - samples/sec: 1992.80 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 03:35:33,557 epoch 10 - iter 432/723 - loss 0.00435067 - time (sec): 52.01 - samples/sec: 2004.72 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 03:35:42,304 epoch 10 - iter 504/723 - loss 0.00425906 - time (sec): 60.75 - samples/sec: 1998.60 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 03:35:51,059 epoch 10 - iter 576/723 - loss 0.00465530 - time (sec): 69.51 - samples/sec: 1988.71 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 03:36:00,064 epoch 10 - iter 648/723 - loss 0.00486187 - time (sec): 78.51 - samples/sec: 1994.27 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 03:36:09,002 epoch 10 - iter 720/723 - loss 0.00532142 - time (sec): 87.45 - samples/sec: 2007.26 - lr: 0.000000 - momentum: 0.000000
+2023-10-25 03:36:09,280 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:36:09,281 EPOCH 10 done: loss 0.0053 - lr: 0.000000
+2023-10-25 03:36:12,707 DEV : loss 0.18416795134544373 - f1-score (micro avg)  0.834
+2023-10-25 03:36:13,192 ----------------------------------------------------------------------------------------------------
+2023-10-25 03:36:13,193 Loading model from best epoch ...
+2023-10-25 03:36:15,267 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
+2023-10-25 03:36:18,515 
+Results:
+- F-score (micro) 0.8085
+- F-score (macro) 0.7291
+- Accuracy 0.69
+
+By class:
+              precision    recall  f1-score   support
+
+         PER     0.8450    0.8029    0.8234       482
+         LOC     0.8802    0.7860    0.8304       458
+         ORG     0.6275    0.4638    0.5333        69
+
+   micro avg     0.8486    0.7721    0.8085      1009
+   macro avg     0.7842    0.6842    0.7291      1009
+weighted avg     0.8461    0.7721    0.8068      1009
+
+2023-10-25 03:36:18,515 ----------------------------------------------------------------------------------------------------