Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,505 @@
+2023-10-24 19:20:16,509 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,510 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 19:20:16,511 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,511 MultiCorpus: 7936 train + 992 dev + 992 test sentences
+ - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/fr
+2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,512 Train:  7936 sentences
+2023-10-24 19:20:16,512         (train_with_dev=False, train_with_test=False)
+2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,512 Training Params:
+2023-10-24 19:20:16,512  - learning_rate: "3e-05" 
+2023-10-24 19:20:16,512  - mini_batch_size: "4"
+2023-10-24 19:20:16,512  - max_epochs: "10"
+2023-10-24 19:20:16,512  - shuffle: "True"
+2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,512 Plugins:
+2023-10-24 19:20:16,512  - TensorboardLogger
+2023-10-24 19:20:16,512  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,512 Final evaluation on model from best epoch (best-model.pt)
+2023-10-24 19:20:16,512  - metric: "('micro avg', 'f1-score')"
+2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,512 Computation:
+2023-10-24 19:20:16,512  - compute on device: cuda:0
+2023-10-24 19:20:16,512  - embedding storage: none
+2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,512 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
+2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,513 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:20:16,513 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-24 19:20:28,549 epoch 1 - iter 198/1984 - loss 1.32014092 - time (sec): 12.04 - samples/sec: 1372.54 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 19:20:40,509 epoch 1 - iter 396/1984 - loss 0.82590169 - time (sec): 24.00 - samples/sec: 1347.40 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 19:20:52,633 epoch 1 - iter 594/1984 - loss 0.62234473 - time (sec): 36.12 - samples/sec: 1359.25 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 19:21:04,703 epoch 1 - iter 792/1984 - loss 0.51779669 - time (sec): 48.19 - samples/sec: 1349.30 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 19:21:16,796 epoch 1 - iter 990/1984 - loss 0.44752052 - time (sec): 60.28 - samples/sec: 1352.27 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 19:21:28,869 epoch 1 - iter 1188/1984 - loss 0.39941383 - time (sec): 72.36 - samples/sec: 1352.98 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 19:21:40,973 epoch 1 - iter 1386/1984 - loss 0.36252978 - time (sec): 84.46 - samples/sec: 1355.89 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 19:21:53,022 epoch 1 - iter 1584/1984 - loss 0.33296148 - time (sec): 96.51 - samples/sec: 1351.32 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 19:22:05,124 epoch 1 - iter 1782/1984 - loss 0.31002868 - time (sec): 108.61 - samples/sec: 1353.86 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 19:22:17,309 epoch 1 - iter 1980/1984 - loss 0.29254745 - time (sec): 120.80 - samples/sec: 1355.42 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 19:22:17,540 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:22:17,540 EPOCH 1 done: loss 0.2922 - lr: 0.000030
+2023-10-24 19:22:20,599 DEV : loss 0.11393631994724274 - f1-score (micro avg)  0.7142
+2023-10-24 19:22:20,614 saving best model
+2023-10-24 19:22:21,081 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:22:33,239 epoch 2 - iter 198/1984 - loss 0.11109567 - time (sec): 12.16 - samples/sec: 1354.61 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 19:22:45,371 epoch 2 - iter 396/1984 - loss 0.11188014 - time (sec): 24.29 - samples/sec: 1357.95 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 19:22:57,459 epoch 2 - iter 594/1984 - loss 0.12088148 - time (sec): 36.38 - samples/sec: 1369.44 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 19:23:09,475 epoch 2 - iter 792/1984 - loss 0.12005888 - time (sec): 48.39 - samples/sec: 1355.48 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 19:23:21,419 epoch 2 - iter 990/1984 - loss 0.11907747 - time (sec): 60.34 - samples/sec: 1344.35 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 19:23:33,494 epoch 2 - iter 1188/1984 - loss 0.11881279 - time (sec): 72.41 - samples/sec: 1342.66 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 19:23:45,448 epoch 2 - iter 1386/1984 - loss 0.11809499 - time (sec): 84.37 - samples/sec: 1344.77 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 19:23:57,836 epoch 2 - iter 1584/1984 - loss 0.11496911 - time (sec): 96.75 - samples/sec: 1350.51 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 19:24:10,044 epoch 2 - iter 1782/1984 - loss 0.11353484 - time (sec): 108.96 - samples/sec: 1347.87 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 19:24:22,155 epoch 2 - iter 1980/1984 - loss 0.11233027 - time (sec): 121.07 - samples/sec: 1353.14 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 19:24:22,383 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:24:22,383 EPOCH 2 done: loss 0.1126 - lr: 0.000027
+2023-10-24 19:24:25,798 DEV : loss 0.11593124270439148 - f1-score (micro avg)  0.7271
+2023-10-24 19:24:25,813 saving best model
+2023-10-24 19:24:26,407 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:24:38,620 epoch 3 - iter 198/1984 - loss 0.08265116 - time (sec): 12.21 - samples/sec: 1416.54 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 19:24:50,809 epoch 3 - iter 396/1984 - loss 0.07804517 - time (sec): 24.40 - samples/sec: 1401.12 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 19:25:03,281 epoch 3 - iter 594/1984 - loss 0.08404645 - time (sec): 36.87 - samples/sec: 1385.28 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 19:25:15,312 epoch 3 - iter 792/1984 - loss 0.08231776 - time (sec): 48.90 - samples/sec: 1359.00 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 19:25:27,283 epoch 3 - iter 990/1984 - loss 0.08429583 - time (sec): 60.87 - samples/sec: 1354.01 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 19:25:39,410 epoch 3 - iter 1188/1984 - loss 0.08375321 - time (sec): 73.00 - samples/sec: 1341.90 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 19:25:51,397 epoch 3 - iter 1386/1984 - loss 0.08571122 - time (sec): 84.99 - samples/sec: 1343.09 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 19:26:03,534 epoch 3 - iter 1584/1984 - loss 0.08551290 - time (sec): 97.13 - samples/sec: 1344.76 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 19:26:15,614 epoch 3 - iter 1782/1984 - loss 0.08579605 - time (sec): 109.21 - samples/sec: 1348.07 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 19:26:27,719 epoch 3 - iter 1980/1984 - loss 0.08549504 - time (sec): 121.31 - samples/sec: 1349.14 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 19:26:27,962 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:26:27,962 EPOCH 3 done: loss 0.0857 - lr: 0.000023
+2023-10-24 19:26:31,075 DEV : loss 0.12287832796573639 - f1-score (micro avg)  0.756
+2023-10-24 19:26:31,090 saving best model
+2023-10-24 19:26:31,684 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:26:43,776 epoch 4 - iter 198/1984 - loss 0.05492174 - time (sec): 12.09 - samples/sec: 1306.03 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 19:26:55,794 epoch 4 - iter 396/1984 - loss 0.06173660 - time (sec): 24.11 - samples/sec: 1325.23 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 19:27:07,916 epoch 4 - iter 594/1984 - loss 0.06108648 - time (sec): 36.23 - samples/sec: 1329.97 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 19:27:19,998 epoch 4 - iter 792/1984 - loss 0.06054768 - time (sec): 48.31 - samples/sec: 1333.58 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 19:27:32,167 epoch 4 - iter 990/1984 - loss 0.06244785 - time (sec): 60.48 - samples/sec: 1341.29 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 19:27:44,204 epoch 4 - iter 1188/1984 - loss 0.06144580 - time (sec): 72.52 - samples/sec: 1342.52 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 19:27:56,373 epoch 4 - iter 1386/1984 - loss 0.06113227 - time (sec): 84.69 - samples/sec: 1348.41 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 19:28:09,135 epoch 4 - iter 1584/1984 - loss 0.06036745 - time (sec): 97.45 - samples/sec: 1352.40 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 19:28:21,273 epoch 4 - iter 1782/1984 - loss 0.06099629 - time (sec): 109.59 - samples/sec: 1351.83 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 19:28:33,327 epoch 4 - iter 1980/1984 - loss 0.06067905 - time (sec): 121.64 - samples/sec: 1346.46 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 19:28:33,553 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:28:33,553 EPOCH 4 done: loss 0.0607 - lr: 0.000020
+2023-10-24 19:28:36,684 DEV : loss 0.1927175521850586 - f1-score (micro avg)  0.7183
+2023-10-24 19:28:36,699 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:28:48,910 epoch 5 - iter 198/1984 - loss 0.04671831 - time (sec): 12.21 - samples/sec: 1361.09 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 19:29:01,027 epoch 5 - iter 396/1984 - loss 0.04574779 - time (sec): 24.33 - samples/sec: 1356.48 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 19:29:13,073 epoch 5 - iter 594/1984 - loss 0.04539830 - time (sec): 36.37 - samples/sec: 1356.89 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 19:29:25,286 epoch 5 - iter 792/1984 - loss 0.04680807 - time (sec): 48.59 - samples/sec: 1358.20 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 19:29:37,625 epoch 5 - iter 990/1984 - loss 0.04441270 - time (sec): 60.93 - samples/sec: 1373.34 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 19:29:49,703 epoch 5 - iter 1188/1984 - loss 0.04380522 - time (sec): 73.00 - samples/sec: 1369.44 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 19:30:02,105 epoch 5 - iter 1386/1984 - loss 0.04443524 - time (sec): 85.41 - samples/sec: 1371.38 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 19:30:14,134 epoch 5 - iter 1584/1984 - loss 0.04578146 - time (sec): 97.43 - samples/sec: 1363.32 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 19:30:26,194 epoch 5 - iter 1782/1984 - loss 0.04603563 - time (sec): 109.49 - samples/sec: 1350.91 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 19:30:38,245 epoch 5 - iter 1980/1984 - loss 0.04522297 - time (sec): 121.55 - samples/sec: 1347.11 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 19:30:38,479 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:30:38,479 EPOCH 5 done: loss 0.0455 - lr: 0.000017
+2023-10-24 19:30:41,600 DEV : loss 0.1995469629764557 - f1-score (micro avg)  0.7543
+2023-10-24 19:30:41,615 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:30:53,777 epoch 6 - iter 198/1984 - loss 0.03231291 - time (sec): 12.16 - samples/sec: 1357.15 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 19:31:05,778 epoch 6 - iter 396/1984 - loss 0.03397784 - time (sec): 24.16 - samples/sec: 1328.30 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 19:31:17,884 epoch 6 - iter 594/1984 - loss 0.03041311 - time (sec): 36.27 - samples/sec: 1346.65 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 19:31:30,370 epoch 6 - iter 792/1984 - loss 0.03190695 - time (sec): 48.75 - samples/sec: 1370.84 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 19:31:42,871 epoch 6 - iter 990/1984 - loss 0.03341697 - time (sec): 61.25 - samples/sec: 1348.17 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 19:31:54,884 epoch 6 - iter 1188/1984 - loss 0.03375744 - time (sec): 73.27 - samples/sec: 1340.20 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 19:32:06,956 epoch 6 - iter 1386/1984 - loss 0.03312953 - time (sec): 85.34 - samples/sec: 1337.39 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 19:32:19,204 epoch 6 - iter 1584/1984 - loss 0.03383901 - time (sec): 97.59 - samples/sec: 1339.64 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 19:32:31,450 epoch 6 - iter 1782/1984 - loss 0.03389974 - time (sec): 109.83 - samples/sec: 1343.73 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 19:32:43,633 epoch 6 - iter 1980/1984 - loss 0.03407852 - time (sec): 122.02 - samples/sec: 1341.61 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 19:32:43,869 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:32:43,870 EPOCH 6 done: loss 0.0340 - lr: 0.000013
+2023-10-24 19:32:46,992 DEV : loss 0.20763596892356873 - f1-score (micro avg)  0.774
+2023-10-24 19:32:47,007 saving best model
+2023-10-24 19:32:47,627 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:32:59,661 epoch 7 - iter 198/1984 - loss 0.02133725 - time (sec): 12.03 - samples/sec: 1354.69 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 19:33:11,642 epoch 7 - iter 396/1984 - loss 0.02091982 - time (sec): 24.01 - samples/sec: 1330.34 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 19:33:23,661 epoch 7 - iter 594/1984 - loss 0.02302967 - time (sec): 36.03 - samples/sec: 1331.94 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 19:33:36,085 epoch 7 - iter 792/1984 - loss 0.02423421 - time (sec): 48.46 - samples/sec: 1350.67 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 19:33:48,050 epoch 7 - iter 990/1984 - loss 0.02379088 - time (sec): 60.42 - samples/sec: 1344.83 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 19:34:00,094 epoch 7 - iter 1188/1984 - loss 0.02343269 - time (sec): 72.47 - samples/sec: 1345.70 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 19:34:12,236 epoch 7 - iter 1386/1984 - loss 0.02524471 - time (sec): 84.61 - samples/sec: 1347.56 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 19:34:24,424 epoch 7 - iter 1584/1984 - loss 0.02464132 - time (sec): 96.80 - samples/sec: 1347.23 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 19:34:36,539 epoch 7 - iter 1782/1984 - loss 0.02431973 - time (sec): 108.91 - samples/sec: 1347.67 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 19:34:48,863 epoch 7 - iter 1980/1984 - loss 0.02469436 - time (sec): 121.23 - samples/sec: 1350.73 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 19:34:49,087 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:34:49,087 EPOCH 7 done: loss 0.0247 - lr: 0.000010
+2023-10-24 19:34:52,192 DEV : loss 0.22793228924274445 - f1-score (micro avg)  0.7628
+2023-10-24 19:34:52,207 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:35:04,591 epoch 8 - iter 198/1984 - loss 0.01770350 - time (sec): 12.38 - samples/sec: 1317.10 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 19:35:16,521 epoch 8 - iter 396/1984 - loss 0.01496629 - time (sec): 24.31 - samples/sec: 1309.49 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 19:35:28,965 epoch 8 - iter 594/1984 - loss 0.01607839 - time (sec): 36.76 - samples/sec: 1345.79 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 19:35:40,927 epoch 8 - iter 792/1984 - loss 0.01770098 - time (sec): 48.72 - samples/sec: 1335.77 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 19:35:53,081 epoch 8 - iter 990/1984 - loss 0.01788262 - time (sec): 60.87 - samples/sec: 1342.78 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 19:36:05,273 epoch 8 - iter 1188/1984 - loss 0.01779408 - time (sec): 73.06 - samples/sec: 1342.96 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 19:36:17,387 epoch 8 - iter 1386/1984 - loss 0.01703299 - time (sec): 85.18 - samples/sec: 1345.43 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 19:36:29,612 epoch 8 - iter 1584/1984 - loss 0.01716121 - time (sec): 97.40 - samples/sec: 1341.02 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 19:36:41,523 epoch 8 - iter 1782/1984 - loss 0.01672368 - time (sec): 109.31 - samples/sec: 1345.12 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 19:36:53,631 epoch 8 - iter 1980/1984 - loss 0.01650254 - time (sec): 121.42 - samples/sec: 1347.56 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 19:36:53,873 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:36:53,873 EPOCH 8 done: loss 0.0165 - lr: 0.000007
+2023-10-24 19:36:56,983 DEV : loss 0.23265020549297333 - f1-score (micro avg)  0.765
+2023-10-24 19:36:56,998 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:37:08,934 epoch 9 - iter 198/1984 - loss 0.01460665 - time (sec): 11.94 - samples/sec: 1310.79 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 19:37:20,956 epoch 9 - iter 396/1984 - loss 0.01489846 - time (sec): 23.96 - samples/sec: 1330.22 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 19:37:32,982 epoch 9 - iter 594/1984 - loss 0.01459467 - time (sec): 35.98 - samples/sec: 1306.08 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 19:37:45,075 epoch 9 - iter 792/1984 - loss 0.01270058 - time (sec): 48.08 - samples/sec: 1327.28 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 19:37:57,137 epoch 9 - iter 990/1984 - loss 0.01265837 - time (sec): 60.14 - samples/sec: 1334.58 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 19:38:09,538 epoch 9 - iter 1188/1984 - loss 0.01297891 - time (sec): 72.54 - samples/sec: 1344.49 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 19:38:21,385 epoch 9 - iter 1386/1984 - loss 0.01248831 - time (sec): 84.39 - samples/sec: 1340.15 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 19:38:33,965 epoch 9 - iter 1584/1984 - loss 0.01258510 - time (sec): 96.97 - samples/sec: 1356.27 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 19:38:46,104 epoch 9 - iter 1782/1984 - loss 0.01225636 - time (sec): 109.11 - samples/sec: 1353.36 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 19:38:58,070 epoch 9 - iter 1980/1984 - loss 0.01210063 - time (sec): 121.07 - samples/sec: 1351.07 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 19:38:58,346 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:38:58,346 EPOCH 9 done: loss 0.0121 - lr: 0.000003
+2023-10-24 19:39:01,778 DEV : loss 0.244042307138443 - f1-score (micro avg)  0.7587
+2023-10-24 19:39:01,793 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:39:14,043 epoch 10 - iter 198/1984 - loss 0.01126873 - time (sec): 12.25 - samples/sec: 1403.09 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 19:39:26,290 epoch 10 - iter 396/1984 - loss 0.01079960 - time (sec): 24.50 - samples/sec: 1376.43 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 19:39:38,492 epoch 10 - iter 594/1984 - loss 0.00920357 - time (sec): 36.70 - samples/sec: 1391.31 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 19:39:50,933 epoch 10 - iter 792/1984 - loss 0.00891660 - time (sec): 49.14 - samples/sec: 1389.24 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 19:40:02,800 epoch 10 - iter 990/1984 - loss 0.00864161 - time (sec): 61.01 - samples/sec: 1368.26 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 19:40:14,924 epoch 10 - iter 1188/1984 - loss 0.00926189 - time (sec): 73.13 - samples/sec: 1364.12 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 19:40:26,822 epoch 10 - iter 1386/1984 - loss 0.00915410 - time (sec): 85.03 - samples/sec: 1349.75 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 19:40:38,890 epoch 10 - iter 1584/1984 - loss 0.00899681 - time (sec): 97.10 - samples/sec: 1349.54 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 19:40:51,050 epoch 10 - iter 1782/1984 - loss 0.00863704 - time (sec): 109.26 - samples/sec: 1350.21 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 19:41:03,100 epoch 10 - iter 1980/1984 - loss 0.00877194 - time (sec): 121.31 - samples/sec: 1348.60 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 19:41:03,350 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:41:03,350 EPOCH 10 done: loss 0.0088 - lr: 0.000000
+2023-10-24 19:41:06,471 DEV : loss 0.25166356563568115 - f1-score (micro avg)  0.7624
+2023-10-24 19:41:06,956 ----------------------------------------------------------------------------------------------------
+2023-10-24 19:41:06,956 Loading model from best epoch ...
+2023-10-24 19:41:08,420 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG
+2023-10-24 19:41:11,490 
+Results:
+- F-score (micro) 0.7761
+- F-score (macro) 0.6778
+- Accuracy 0.6586
+
+By class:
+              precision    recall  f1-score   support
+
+         LOC     0.8447    0.8305    0.8376       655
+         PER     0.6996    0.7937    0.7437       223
+         ORG     0.6250    0.3543    0.4523       127
+
+   micro avg     0.7905    0.7622    0.7761      1005
+   macro avg     0.7231    0.6595    0.6778      1005
+weighted avg     0.7848    0.7622    0.7680      1005
+
+2023-10-24 19:41:11,490 ----------------------------------------------------------------------------------------------------