Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,508 @@
+2023-10-24 14:31:22,491 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,493 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 14:31:22,493 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,493 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 14:31:22,493 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,493 Train:  7936 sentences
+2023-10-24 14:31:22,493         (train_with_dev=False, train_with_test=False)
+2023-10-24 14:31:22,493 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,493 Training Params:
+2023-10-24 14:31:22,493  - learning_rate: "3e-05" 
+2023-10-24 14:31:22,493  - mini_batch_size: "4"
+2023-10-24 14:31:22,493  - max_epochs: "10"
+2023-10-24 14:31:22,493  - shuffle: "True"
+2023-10-24 14:31:22,493 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,493 Plugins:
+2023-10-24 14:31:22,493  - TensorboardLogger
+2023-10-24 14:31:22,493  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-24 14:31:22,493 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,493 Final evaluation on model from best epoch (best-model.pt)
+2023-10-24 14:31:22,493  - metric: "('micro avg', 'f1-score')"
+2023-10-24 14:31:22,493 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,493 Computation:
+2023-10-24 14:31:22,493  - compute on device: cuda:0
+2023-10-24 14:31:22,494  - embedding storage: none
+2023-10-24 14:31:22,494 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,494 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
+2023-10-24 14:31:22,494 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,494 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:31:22,494 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-24 14:31:34,835 epoch 1 - iter 198/1984 - loss 1.64021175 - time (sec): 12.34 - samples/sec: 1274.19 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 14:31:46,520 epoch 1 - iter 396/1984 - loss 0.98613041 - time (sec): 24.03 - samples/sec: 1291.18 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 14:31:58,355 epoch 1 - iter 594/1984 - loss 0.72657281 - time (sec): 35.86 - samples/sec: 1322.15 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 14:32:10,143 epoch 1 - iter 792/1984 - loss 0.58763880 - time (sec): 47.65 - samples/sec: 1329.63 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 14:32:22,176 epoch 1 - iter 990/1984 - loss 0.49473459 - time (sec): 59.68 - samples/sec: 1350.76 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 14:32:34,199 epoch 1 - iter 1188/1984 - loss 0.43574145 - time (sec): 71.70 - samples/sec: 1353.56 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 14:32:46,538 epoch 1 - iter 1386/1984 - loss 0.39286382 - time (sec): 84.04 - samples/sec: 1350.90 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 14:32:58,675 epoch 1 - iter 1584/1984 - loss 0.36073738 - time (sec): 96.18 - samples/sec: 1358.30 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 14:33:10,706 epoch 1 - iter 1782/1984 - loss 0.33631924 - time (sec): 108.21 - samples/sec: 1360.63 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 14:33:22,689 epoch 1 - iter 1980/1984 - loss 0.31569591 - time (sec): 120.19 - samples/sec: 1361.86 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 14:33:22,927 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:33:22,927 EPOCH 1 done: loss 0.3154 - lr: 0.000030
+2023-10-24 14:33:25,939 DEV : loss 0.09478097409009933 - f1-score (micro avg)  0.7144
+2023-10-24 14:33:25,953 saving best model
+2023-10-24 14:33:26,514 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:33:38,596 epoch 2 - iter 198/1984 - loss 0.11789057 - time (sec): 12.08 - samples/sec: 1412.70 - lr: 0.000030 - momentum: 0.000000
+2023-10-24 14:33:50,643 epoch 2 - iter 396/1984 - loss 0.12637511 - time (sec): 24.13 - samples/sec: 1385.10 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 14:34:02,939 epoch 2 - iter 594/1984 - loss 0.12285469 - time (sec): 36.42 - samples/sec: 1395.18 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 14:34:14,859 epoch 2 - iter 792/1984 - loss 0.11931934 - time (sec): 48.34 - samples/sec: 1383.19 - lr: 0.000029 - momentum: 0.000000
+2023-10-24 14:34:26,987 epoch 2 - iter 990/1984 - loss 0.11648264 - time (sec): 60.47 - samples/sec: 1377.44 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 14:34:39,006 epoch 2 - iter 1188/1984 - loss 0.11833590 - time (sec): 72.49 - samples/sec: 1358.53 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 14:34:50,954 epoch 2 - iter 1386/1984 - loss 0.11886180 - time (sec): 84.44 - samples/sec: 1351.97 - lr: 0.000028 - momentum: 0.000000
+2023-10-24 14:35:03,035 epoch 2 - iter 1584/1984 - loss 0.11758701 - time (sec): 96.52 - samples/sec: 1350.28 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 14:35:15,270 epoch 2 - iter 1782/1984 - loss 0.11634270 - time (sec): 108.76 - samples/sec: 1353.72 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 14:35:27,311 epoch 2 - iter 1980/1984 - loss 0.11438214 - time (sec): 120.80 - samples/sec: 1354.91 - lr: 0.000027 - momentum: 0.000000
+2023-10-24 14:35:27,547 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:35:27,547 EPOCH 2 done: loss 0.1142 - lr: 0.000027
+2023-10-24 14:35:30,641 DEV : loss 0.10835588723421097 - f1-score (micro avg)  0.7283
+2023-10-24 14:35:30,656 saving best model
+2023-10-24 14:35:31,361 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:35:43,401 epoch 3 - iter 198/1984 - loss 0.07469050 - time (sec): 12.04 - samples/sec: 1319.96 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 14:35:55,496 epoch 3 - iter 396/1984 - loss 0.07599030 - time (sec): 24.13 - samples/sec: 1364.30 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 14:36:07,686 epoch 3 - iter 594/1984 - loss 0.07603147 - time (sec): 36.32 - samples/sec: 1368.90 - lr: 0.000026 - momentum: 0.000000
+2023-10-24 14:36:19,765 epoch 3 - iter 792/1984 - loss 0.08234754 - time (sec): 48.40 - samples/sec: 1349.84 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 14:36:31,750 epoch 3 - iter 990/1984 - loss 0.08578592 - time (sec): 60.39 - samples/sec: 1343.02 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 14:36:44,036 epoch 3 - iter 1188/1984 - loss 0.08858337 - time (sec): 72.67 - samples/sec: 1342.52 - lr: 0.000025 - momentum: 0.000000
+2023-10-24 14:36:55,947 epoch 3 - iter 1386/1984 - loss 0.09044162 - time (sec): 84.59 - samples/sec: 1337.62 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 14:37:08,165 epoch 3 - iter 1584/1984 - loss 0.08919442 - time (sec): 96.80 - samples/sec: 1343.55 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 14:37:20,537 epoch 3 - iter 1782/1984 - loss 0.08855403 - time (sec): 109.18 - samples/sec: 1338.97 - lr: 0.000024 - momentum: 0.000000
+2023-10-24 14:37:32,948 epoch 3 - iter 1980/1984 - loss 0.08691521 - time (sec): 121.59 - samples/sec: 1345.37 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 14:37:33,202 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:37:33,202 EPOCH 3 done: loss 0.0871 - lr: 0.000023
+2023-10-24 14:37:36,304 DEV : loss 0.13157667219638824 - f1-score (micro avg)  0.7364
+2023-10-24 14:37:36,319 saving best model
+2023-10-24 14:37:36,975 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:37:49,088 epoch 4 - iter 198/1984 - loss 0.06040276 - time (sec): 12.11 - samples/sec: 1376.76 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 14:38:01,271 epoch 4 - iter 396/1984 - loss 0.05539813 - time (sec): 24.29 - samples/sec: 1354.61 - lr: 0.000023 - momentum: 0.000000
+2023-10-24 14:38:13,104 epoch 4 - iter 594/1984 - loss 0.05490719 - time (sec): 36.13 - samples/sec: 1330.15 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 14:38:25,121 epoch 4 - iter 792/1984 - loss 0.06133338 - time (sec): 48.14 - samples/sec: 1335.44 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 14:38:37,262 epoch 4 - iter 990/1984 - loss 0.06105312 - time (sec): 60.29 - samples/sec: 1344.03 - lr: 0.000022 - momentum: 0.000000
+2023-10-24 14:38:49,881 epoch 4 - iter 1188/1984 - loss 0.06152759 - time (sec): 72.90 - samples/sec: 1362.84 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 14:39:01,795 epoch 4 - iter 1386/1984 - loss 0.06044022 - time (sec): 84.82 - samples/sec: 1358.01 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 14:39:13,983 epoch 4 - iter 1584/1984 - loss 0.06312833 - time (sec): 97.01 - samples/sec: 1358.54 - lr: 0.000021 - momentum: 0.000000
+2023-10-24 14:39:26,132 epoch 4 - iter 1782/1984 - loss 0.06372263 - time (sec): 109.16 - samples/sec: 1355.91 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 14:39:38,115 epoch 4 - iter 1980/1984 - loss 0.06435156 - time (sec): 121.14 - samples/sec: 1351.58 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 14:39:38,347 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:39:38,347 EPOCH 4 done: loss 0.0645 - lr: 0.000020
+2023-10-24 14:39:41,437 DEV : loss 0.19480304419994354 - f1-score (micro avg)  0.74
+2023-10-24 14:39:41,451 saving best model
+2023-10-24 14:39:42,159 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:39:54,466 epoch 5 - iter 198/1984 - loss 0.05026390 - time (sec): 12.31 - samples/sec: 1372.20 - lr: 0.000020 - momentum: 0.000000
+2023-10-24 14:40:06,513 epoch 5 - iter 396/1984 - loss 0.04926928 - time (sec): 24.35 - samples/sec: 1349.95 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 14:40:18,489 epoch 5 - iter 594/1984 - loss 0.04643126 - time (sec): 36.33 - samples/sec: 1343.01 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 14:40:30,764 epoch 5 - iter 792/1984 - loss 0.04774956 - time (sec): 48.60 - samples/sec: 1360.83 - lr: 0.000019 - momentum: 0.000000
+2023-10-24 14:40:42,974 epoch 5 - iter 990/1984 - loss 0.04725796 - time (sec): 60.81 - samples/sec: 1339.73 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 14:40:55,011 epoch 5 - iter 1188/1984 - loss 0.04580115 - time (sec): 72.85 - samples/sec: 1341.47 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 14:41:07,111 epoch 5 - iter 1386/1984 - loss 0.04453556 - time (sec): 84.95 - samples/sec: 1344.63 - lr: 0.000018 - momentum: 0.000000
+2023-10-24 14:41:19,265 epoch 5 - iter 1584/1984 - loss 0.04431866 - time (sec): 97.10 - samples/sec: 1350.72 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 14:41:31,590 epoch 5 - iter 1782/1984 - loss 0.04476987 - time (sec): 109.43 - samples/sec: 1353.50 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 14:41:43,646 epoch 5 - iter 1980/1984 - loss 0.04463271 - time (sec): 121.49 - samples/sec: 1348.16 - lr: 0.000017 - momentum: 0.000000
+2023-10-24 14:41:43,874 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:41:43,874 EPOCH 5 done: loss 0.0447 - lr: 0.000017
+2023-10-24 14:41:46,984 DEV : loss 0.18662182986736298 - f1-score (micro avg)  0.7517
+2023-10-24 14:41:46,999 saving best model
+2023-10-24 14:41:47,695 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:41:59,786 epoch 6 - iter 198/1984 - loss 0.02967304 - time (sec): 12.09 - samples/sec: 1328.35 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 14:42:11,835 epoch 6 - iter 396/1984 - loss 0.02628259 - time (sec): 24.14 - samples/sec: 1339.14 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 14:42:24,130 epoch 6 - iter 594/1984 - loss 0.03178036 - time (sec): 36.43 - samples/sec: 1353.58 - lr: 0.000016 - momentum: 0.000000
+2023-10-24 14:42:36,229 epoch 6 - iter 792/1984 - loss 0.03031091 - time (sec): 48.53 - samples/sec: 1343.45 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 14:42:48,393 epoch 6 - iter 990/1984 - loss 0.03339443 - time (sec): 60.70 - samples/sec: 1357.58 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 14:43:00,431 epoch 6 - iter 1188/1984 - loss 0.03520672 - time (sec): 72.73 - samples/sec: 1355.98 - lr: 0.000015 - momentum: 0.000000
+2023-10-24 14:43:12,544 epoch 6 - iter 1386/1984 - loss 0.03507182 - time (sec): 84.85 - samples/sec: 1355.23 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 14:43:24,608 epoch 6 - iter 1584/1984 - loss 0.03513777 - time (sec): 96.91 - samples/sec: 1351.09 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 14:43:36,845 epoch 6 - iter 1782/1984 - loss 0.03572007 - time (sec): 109.15 - samples/sec: 1347.12 - lr: 0.000014 - momentum: 0.000000
+2023-10-24 14:43:49,108 epoch 6 - iter 1980/1984 - loss 0.03503102 - time (sec): 121.41 - samples/sec: 1349.11 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 14:43:49,334 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:43:49,334 EPOCH 6 done: loss 0.0350 - lr: 0.000013
+2023-10-24 14:43:52,429 DEV : loss 0.21698078513145447 - f1-score (micro avg)  0.7558
+2023-10-24 14:43:52,443 saving best model
+2023-10-24 14:43:53,142 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:44:05,593 epoch 7 - iter 198/1984 - loss 0.02040662 - time (sec): 12.45 - samples/sec: 1367.24 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 14:44:17,602 epoch 7 - iter 396/1984 - loss 0.02479863 - time (sec): 24.46 - samples/sec: 1339.10 - lr: 0.000013 - momentum: 0.000000
+2023-10-24 14:44:29,624 epoch 7 - iter 594/1984 - loss 0.02452452 - time (sec): 36.48 - samples/sec: 1320.81 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 14:44:41,592 epoch 7 - iter 792/1984 - loss 0.02504432 - time (sec): 48.45 - samples/sec: 1317.92 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 14:44:53,589 epoch 7 - iter 990/1984 - loss 0.02388568 - time (sec): 60.45 - samples/sec: 1311.14 - lr: 0.000012 - momentum: 0.000000
+2023-10-24 14:45:05,715 epoch 7 - iter 1188/1984 - loss 0.02418482 - time (sec): 72.57 - samples/sec: 1325.54 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 14:45:17,830 epoch 7 - iter 1386/1984 - loss 0.02431743 - time (sec): 84.69 - samples/sec: 1329.80 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 14:45:29,872 epoch 7 - iter 1584/1984 - loss 0.02469299 - time (sec): 96.73 - samples/sec: 1328.05 - lr: 0.000011 - momentum: 0.000000
+2023-10-24 14:45:42,461 epoch 7 - iter 1782/1984 - loss 0.02487510 - time (sec): 109.32 - samples/sec: 1339.43 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 14:45:54,623 epoch 7 - iter 1980/1984 - loss 0.02496138 - time (sec): 121.48 - samples/sec: 1348.11 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 14:45:54,851 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:45:54,851 EPOCH 7 done: loss 0.0249 - lr: 0.000010
+2023-10-24 14:45:57,960 DEV : loss 0.22160428762435913 - f1-score (micro avg)  0.7497
+2023-10-24 14:45:57,975 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:46:10,073 epoch 8 - iter 198/1984 - loss 0.01209168 - time (sec): 12.10 - samples/sec: 1363.85 - lr: 0.000010 - momentum: 0.000000
+2023-10-24 14:46:21,985 epoch 8 - iter 396/1984 - loss 0.01639127 - time (sec): 24.01 - samples/sec: 1311.69 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 14:46:34,041 epoch 8 - iter 594/1984 - loss 0.01756574 - time (sec): 36.07 - samples/sec: 1317.22 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 14:46:46,342 epoch 8 - iter 792/1984 - loss 0.01608469 - time (sec): 48.37 - samples/sec: 1327.24 - lr: 0.000009 - momentum: 0.000000
+2023-10-24 14:46:58,745 epoch 8 - iter 990/1984 - loss 0.01710028 - time (sec): 60.77 - samples/sec: 1342.92 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 14:47:10,850 epoch 8 - iter 1188/1984 - loss 0.01724256 - time (sec): 72.87 - samples/sec: 1342.88 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 14:47:23,213 epoch 8 - iter 1386/1984 - loss 0.01610726 - time (sec): 85.24 - samples/sec: 1359.59 - lr: 0.000008 - momentum: 0.000000
+2023-10-24 14:47:35,153 epoch 8 - iter 1584/1984 - loss 0.01637683 - time (sec): 97.18 - samples/sec: 1348.61 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 14:47:47,301 epoch 8 - iter 1782/1984 - loss 0.01694080 - time (sec): 109.33 - samples/sec: 1350.21 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 14:47:59,271 epoch 8 - iter 1980/1984 - loss 0.01660634 - time (sec): 121.30 - samples/sec: 1348.03 - lr: 0.000007 - momentum: 0.000000
+2023-10-24 14:47:59,545 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:47:59,545 EPOCH 8 done: loss 0.0166 - lr: 0.000007
+2023-10-24 14:48:02,962 DEV : loss 0.23455536365509033 - f1-score (micro avg)  0.7546
+2023-10-24 14:48:02,977 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:48:15,195 epoch 9 - iter 198/1984 - loss 0.00905006 - time (sec): 12.22 - samples/sec: 1411.26 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 14:48:27,508 epoch 9 - iter 396/1984 - loss 0.00911175 - time (sec): 24.53 - samples/sec: 1385.96 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 14:48:39,556 epoch 9 - iter 594/1984 - loss 0.01007165 - time (sec): 36.58 - samples/sec: 1379.07 - lr: 0.000006 - momentum: 0.000000
+2023-10-24 14:48:51,753 epoch 9 - iter 792/1984 - loss 0.01181057 - time (sec): 48.77 - samples/sec: 1370.89 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 14:49:03,817 epoch 9 - iter 990/1984 - loss 0.01269583 - time (sec): 60.84 - samples/sec: 1365.37 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 14:49:16,171 epoch 9 - iter 1188/1984 - loss 0.01342504 - time (sec): 73.19 - samples/sec: 1372.60 - lr: 0.000005 - momentum: 0.000000
+2023-10-24 14:49:28,166 epoch 9 - iter 1386/1984 - loss 0.01277923 - time (sec): 85.19 - samples/sec: 1363.74 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 14:49:40,133 epoch 9 - iter 1584/1984 - loss 0.01264028 - time (sec): 97.15 - samples/sec: 1356.06 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 14:49:52,112 epoch 9 - iter 1782/1984 - loss 0.01278804 - time (sec): 109.13 - samples/sec: 1351.36 - lr: 0.000004 - momentum: 0.000000
+2023-10-24 14:50:04,183 epoch 9 - iter 1980/1984 - loss 0.01271379 - time (sec): 121.20 - samples/sec: 1350.44 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 14:50:04,438 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:50:04,438 EPOCH 9 done: loss 0.0127 - lr: 0.000003
+2023-10-24 14:50:07,546 DEV : loss 0.24538028240203857 - f1-score (micro avg)  0.7562
+2023-10-24 14:50:07,561 saving best model
+2023-10-24 14:50:08,407 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:50:20,305 epoch 10 - iter 198/1984 - loss 0.01102981 - time (sec): 11.90 - samples/sec: 1336.30 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 14:50:32,270 epoch 10 - iter 396/1984 - loss 0.00908295 - time (sec): 23.86 - samples/sec: 1337.17 - lr: 0.000003 - momentum: 0.000000
+2023-10-24 14:50:44,607 epoch 10 - iter 594/1984 - loss 0.00884709 - time (sec): 36.20 - samples/sec: 1365.66 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 14:50:56,745 epoch 10 - iter 792/1984 - loss 0.00853659 - time (sec): 48.34 - samples/sec: 1358.97 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 14:51:08,846 epoch 10 - iter 990/1984 - loss 0.00836767 - time (sec): 60.44 - samples/sec: 1359.78 - lr: 0.000002 - momentum: 0.000000
+2023-10-24 14:51:20,973 epoch 10 - iter 1188/1984 - loss 0.00884835 - time (sec): 72.56 - samples/sec: 1363.32 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 14:51:33,018 epoch 10 - iter 1386/1984 - loss 0.00855372 - time (sec): 84.61 - samples/sec: 1354.25 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 14:51:45,186 epoch 10 - iter 1584/1984 - loss 0.00850122 - time (sec): 96.78 - samples/sec: 1351.56 - lr: 0.000001 - momentum: 0.000000
+2023-10-24 14:51:57,670 epoch 10 - iter 1782/1984 - loss 0.00808050 - time (sec): 109.26 - samples/sec: 1347.29 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 14:52:09,831 epoch 10 - iter 1980/1984 - loss 0.00833862 - time (sec): 121.42 - samples/sec: 1346.80 - lr: 0.000000 - momentum: 0.000000
+2023-10-24 14:52:10,101 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:52:10,101 EPOCH 10 done: loss 0.0083 - lr: 0.000000
+2023-10-24 14:52:13,220 DEV : loss 0.24850758910179138 - f1-score (micro avg)  0.7547
+2023-10-24 14:52:13,792 ----------------------------------------------------------------------------------------------------
+2023-10-24 14:52:13,793 Loading model from best epoch ...
+2023-10-24 14:52:15,747 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 14:52:18,813 
+Results:
+- F-score (micro) 0.7945
+- F-score (macro) 0.7119
+- Accuracy 0.6818
+
+By class:
+              precision    recall  f1-score   support
+
+         LOC     0.8256    0.8748    0.8495       655
+         PER     0.7366    0.8027    0.7682       223
+         ORG     0.5979    0.4567    0.5179       127
+
+   micro avg     0.7834    0.8060    0.7945      1005
+   macro avg     0.7201    0.7114    0.7119      1005
+weighted avg     0.7771    0.8060    0.7896      1005
+
+2023-10-24 14:52:18,814 ----------------------------------------------------------------------------------------------------