Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,510 @@
+2023-10-23 20:53:59,183 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,184 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=21, bias=True)
+  (loss_function): CrossEntropyLoss()
+)"
+2023-10-23 20:53:59,184 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,184 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
+2023-10-23 20:53:59,184 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,184 Train:  3575 sentences
+2023-10-23 20:53:59,184         (train_with_dev=False, train_with_test=False)
+2023-10-23 20:53:59,184 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,184 Training Params:
+2023-10-23 20:53:59,184  - learning_rate: "5e-05" 
+2023-10-23 20:53:59,184  - mini_batch_size: "4"
+2023-10-23 20:53:59,184  - max_epochs: "10"
+2023-10-23 20:53:59,184  - shuffle: "True"
+2023-10-23 20:53:59,184 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,184 Plugins:
+2023-10-23 20:53:59,185  - TensorboardLogger
+2023-10-23 20:53:59,185  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-23 20:53:59,185 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,185 Final evaluation on model from best epoch (best-model.pt)
+2023-10-23 20:53:59,185  - metric: "('micro avg', 'f1-score')"
+2023-10-23 20:53:59,185 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,185 Computation:
+2023-10-23 20:53:59,185  - compute on device: cuda:0
+2023-10-23 20:53:59,185  - embedding storage: none
+2023-10-23 20:53:59,185 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,185 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
+2023-10-23 20:53:59,185 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,185 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:53:59,185 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-23 20:54:04,695 epoch 1 - iter 89/894 - loss 2.05648241 - time (sec): 5.51 - samples/sec: 1445.62 - lr: 0.000005 - momentum: 0.000000
+2023-10-23 20:54:10,399 epoch 1 - iter 178/894 - loss 1.21404748 - time (sec): 11.21 - samples/sec: 1485.36 - lr: 0.000010 - momentum: 0.000000
+2023-10-23 20:54:16,086 epoch 1 - iter 267/894 - loss 0.90628017 - time (sec): 16.90 - samples/sec: 1488.84 - lr: 0.000015 - momentum: 0.000000
+2023-10-23 20:54:21,773 epoch 1 - iter 356/894 - loss 0.76044414 - time (sec): 22.59 - samples/sec: 1492.63 - lr: 0.000020 - momentum: 0.000000
+2023-10-23 20:54:27,374 epoch 1 - iter 445/894 - loss 0.66552201 - time (sec): 28.19 - samples/sec: 1501.30 - lr: 0.000025 - momentum: 0.000000
+2023-10-23 20:54:32,883 epoch 1 - iter 534/894 - loss 0.60071179 - time (sec): 33.70 - samples/sec: 1495.06 - lr: 0.000030 - momentum: 0.000000
+2023-10-23 20:54:38,479 epoch 1 - iter 623/894 - loss 0.54372354 - time (sec): 39.29 - samples/sec: 1500.03 - lr: 0.000035 - momentum: 0.000000
+2023-10-23 20:54:44,124 epoch 1 - iter 712/894 - loss 0.50080113 - time (sec): 44.94 - samples/sec: 1504.45 - lr: 0.000040 - momentum: 0.000000
+2023-10-23 20:54:50,084 epoch 1 - iter 801/894 - loss 0.46387916 - time (sec): 50.90 - samples/sec: 1517.16 - lr: 0.000045 - momentum: 0.000000
+2023-10-23 20:54:55,699 epoch 1 - iter 890/894 - loss 0.43757430 - time (sec): 56.51 - samples/sec: 1526.27 - lr: 0.000050 - momentum: 0.000000
+2023-10-23 20:54:55,932 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:54:55,932 EPOCH 1 done: loss 0.4371 - lr: 0.000050
+2023-10-23 20:55:00,775 DEV : loss 0.1591983586549759 - f1-score (micro avg)  0.6143
+2023-10-23 20:55:00,795 saving best model
+2023-10-23 20:55:01,267 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:55:06,720 epoch 2 - iter 89/894 - loss 0.16974048 - time (sec): 5.45 - samples/sec: 1518.20 - lr: 0.000049 - momentum: 0.000000
+2023-10-23 20:55:12,416 epoch 2 - iter 178/894 - loss 0.16143225 - time (sec): 11.15 - samples/sec: 1525.41 - lr: 0.000049 - momentum: 0.000000
+2023-10-23 20:55:18,123 epoch 2 - iter 267/894 - loss 0.15180311 - time (sec): 16.85 - samples/sec: 1537.73 - lr: 0.000048 - momentum: 0.000000
+2023-10-23 20:55:23,889 epoch 2 - iter 356/894 - loss 0.15236701 - time (sec): 22.62 - samples/sec: 1532.24 - lr: 0.000048 - momentum: 0.000000
+2023-10-23 20:55:29,405 epoch 2 - iter 445/894 - loss 0.14334298 - time (sec): 28.14 - samples/sec: 1509.83 - lr: 0.000047 - momentum: 0.000000
+2023-10-23 20:55:35,194 epoch 2 - iter 534/894 - loss 0.15247437 - time (sec): 33.93 - samples/sec: 1517.25 - lr: 0.000047 - momentum: 0.000000
+2023-10-23 20:55:40,912 epoch 2 - iter 623/894 - loss 0.14975823 - time (sec): 39.64 - samples/sec: 1525.54 - lr: 0.000046 - momentum: 0.000000
+2023-10-23 20:55:46,390 epoch 2 - iter 712/894 - loss 0.14876006 - time (sec): 45.12 - samples/sec: 1514.34 - lr: 0.000046 - momentum: 0.000000
+2023-10-23 20:55:52,336 epoch 2 - iter 801/894 - loss 0.14878889 - time (sec): 51.07 - samples/sec: 1525.36 - lr: 0.000045 - momentum: 0.000000
+2023-10-23 20:55:57,878 epoch 2 - iter 890/894 - loss 0.14578259 - time (sec): 56.61 - samples/sec: 1520.97 - lr: 0.000044 - momentum: 0.000000
+2023-10-23 20:55:58,141 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:55:58,141 EPOCH 2 done: loss 0.1456 - lr: 0.000044
+2023-10-23 20:56:04,638 DEV : loss 0.22977472841739655 - f1-score (micro avg)  0.6806
+2023-10-23 20:56:04,659 saving best model
+2023-10-23 20:56:05,256 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:56:11,024 epoch 3 - iter 89/894 - loss 0.10865051 - time (sec): 5.77 - samples/sec: 1553.30 - lr: 0.000044 - momentum: 0.000000
+2023-10-23 20:56:16,764 epoch 3 - iter 178/894 - loss 0.11003605 - time (sec): 11.51 - samples/sec: 1535.17 - lr: 0.000043 - momentum: 0.000000
+2023-10-23 20:56:22,515 epoch 3 - iter 267/894 - loss 0.10395964 - time (sec): 17.26 - samples/sec: 1555.50 - lr: 0.000043 - momentum: 0.000000
+2023-10-23 20:56:28,133 epoch 3 - iter 356/894 - loss 0.09794376 - time (sec): 22.88 - samples/sec: 1524.17 - lr: 0.000042 - momentum: 0.000000
+2023-10-23 20:56:33,749 epoch 3 - iter 445/894 - loss 0.09527822 - time (sec): 28.49 - samples/sec: 1527.06 - lr: 0.000042 - momentum: 0.000000
+2023-10-23 20:56:39,381 epoch 3 - iter 534/894 - loss 0.09373453 - time (sec): 34.12 - samples/sec: 1519.68 - lr: 0.000041 - momentum: 0.000000
+2023-10-23 20:56:44,925 epoch 3 - iter 623/894 - loss 0.09364125 - time (sec): 39.67 - samples/sec: 1511.34 - lr: 0.000041 - momentum: 0.000000
+2023-10-23 20:56:50,828 epoch 3 - iter 712/894 - loss 0.09013864 - time (sec): 45.57 - samples/sec: 1518.87 - lr: 0.000040 - momentum: 0.000000
+2023-10-23 20:56:56,436 epoch 3 - iter 801/894 - loss 0.09096854 - time (sec): 51.18 - samples/sec: 1513.59 - lr: 0.000039 - momentum: 0.000000
+2023-10-23 20:57:02,199 epoch 3 - iter 890/894 - loss 0.08996061 - time (sec): 56.94 - samples/sec: 1514.41 - lr: 0.000039 - momentum: 0.000000
+2023-10-23 20:57:02,431 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:57:02,431 EPOCH 3 done: loss 0.0898 - lr: 0.000039
+2023-10-23 20:57:08,939 DEV : loss 0.19408421218395233 - f1-score (micro avg)  0.7459
+2023-10-23 20:57:08,960 saving best model
+2023-10-23 20:57:09,557 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:57:15,087 epoch 4 - iter 89/894 - loss 0.07126826 - time (sec): 5.53 - samples/sec: 1467.85 - lr: 0.000038 - momentum: 0.000000
+2023-10-23 20:57:20,786 epoch 4 - iter 178/894 - loss 0.06075018 - time (sec): 11.23 - samples/sec: 1492.76 - lr: 0.000038 - momentum: 0.000000
+2023-10-23 20:57:26,437 epoch 4 - iter 267/894 - loss 0.05637859 - time (sec): 16.88 - samples/sec: 1508.80 - lr: 0.000037 - momentum: 0.000000
+2023-10-23 20:57:32,295 epoch 4 - iter 356/894 - loss 0.05891890 - time (sec): 22.74 - samples/sec: 1518.14 - lr: 0.000037 - momentum: 0.000000
+2023-10-23 20:57:38,003 epoch 4 - iter 445/894 - loss 0.06114642 - time (sec): 28.44 - samples/sec: 1512.47 - lr: 0.000036 - momentum: 0.000000
+2023-10-23 20:57:43,730 epoch 4 - iter 534/894 - loss 0.06236999 - time (sec): 34.17 - samples/sec: 1514.92 - lr: 0.000036 - momentum: 0.000000
+2023-10-23 20:57:49,533 epoch 4 - iter 623/894 - loss 0.06392335 - time (sec): 39.97 - samples/sec: 1525.05 - lr: 0.000035 - momentum: 0.000000
+2023-10-23 20:57:55,255 epoch 4 - iter 712/894 - loss 0.06295692 - time (sec): 45.70 - samples/sec: 1526.07 - lr: 0.000034 - momentum: 0.000000
+2023-10-23 20:58:00,800 epoch 4 - iter 801/894 - loss 0.06292309 - time (sec): 51.24 - samples/sec: 1518.26 - lr: 0.000034 - momentum: 0.000000
+2023-10-23 20:58:06,323 epoch 4 - iter 890/894 - loss 0.06266573 - time (sec): 56.76 - samples/sec: 1518.51 - lr: 0.000033 - momentum: 0.000000
+2023-10-23 20:58:06,577 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:58:06,577 EPOCH 4 done: loss 0.0631 - lr: 0.000033
+2023-10-23 20:58:13,122 DEV : loss 0.22660154104232788 - f1-score (micro avg)  0.7247
+2023-10-23 20:58:13,143 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:58:18,820 epoch 5 - iter 89/894 - loss 0.03574570 - time (sec): 5.68 - samples/sec: 1548.77 - lr: 0.000033 - momentum: 0.000000
+2023-10-23 20:58:24,508 epoch 5 - iter 178/894 - loss 0.03970603 - time (sec): 11.36 - samples/sec: 1500.75 - lr: 0.000032 - momentum: 0.000000
+2023-10-23 20:58:30,000 epoch 5 - iter 267/894 - loss 0.04068036 - time (sec): 16.86 - samples/sec: 1487.29 - lr: 0.000032 - momentum: 0.000000
+2023-10-23 20:58:35,851 epoch 5 - iter 356/894 - loss 0.04525724 - time (sec): 22.71 - samples/sec: 1521.43 - lr: 0.000031 - momentum: 0.000000
+2023-10-23 20:58:41,423 epoch 5 - iter 445/894 - loss 0.04526026 - time (sec): 28.28 - samples/sec: 1507.73 - lr: 0.000031 - momentum: 0.000000
+2023-10-23 20:58:46,970 epoch 5 - iter 534/894 - loss 0.04516609 - time (sec): 33.83 - samples/sec: 1503.75 - lr: 0.000030 - momentum: 0.000000
+2023-10-23 20:58:52,901 epoch 5 - iter 623/894 - loss 0.04404538 - time (sec): 39.76 - samples/sec: 1518.02 - lr: 0.000029 - momentum: 0.000000
+2023-10-23 20:58:58,571 epoch 5 - iter 712/894 - loss 0.04347653 - time (sec): 45.43 - samples/sec: 1519.94 - lr: 0.000029 - momentum: 0.000000
+2023-10-23 20:59:04,172 epoch 5 - iter 801/894 - loss 0.04427952 - time (sec): 51.03 - samples/sec: 1526.89 - lr: 0.000028 - momentum: 0.000000
+2023-10-23 20:59:09,706 epoch 5 - iter 890/894 - loss 0.04395567 - time (sec): 56.56 - samples/sec: 1523.08 - lr: 0.000028 - momentum: 0.000000
+2023-10-23 20:59:09,959 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:59:09,959 EPOCH 5 done: loss 0.0440 - lr: 0.000028
+2023-10-23 20:59:16,476 DEV : loss 0.2578391432762146 - f1-score (micro avg)  0.7454
+2023-10-23 20:59:16,496 ----------------------------------------------------------------------------------------------------
+2023-10-23 20:59:22,046 epoch 6 - iter 89/894 - loss 0.02996543 - time (sec): 5.55 - samples/sec: 1443.43 - lr: 0.000027 - momentum: 0.000000
+2023-10-23 20:59:27,682 epoch 6 - iter 178/894 - loss 0.02468163 - time (sec): 11.19 - samples/sec: 1441.23 - lr: 0.000027 - momentum: 0.000000
+2023-10-23 20:59:33,444 epoch 6 - iter 267/894 - loss 0.02950738 - time (sec): 16.95 - samples/sec: 1480.05 - lr: 0.000026 - momentum: 0.000000
+2023-10-23 20:59:39,138 epoch 6 - iter 356/894 - loss 0.02848739 - time (sec): 22.64 - samples/sec: 1520.93 - lr: 0.000026 - momentum: 0.000000
+2023-10-23 20:59:44,762 epoch 6 - iter 445/894 - loss 0.02765367 - time (sec): 28.27 - samples/sec: 1524.43 - lr: 0.000025 - momentum: 0.000000
+2023-10-23 20:59:50,448 epoch 6 - iter 534/894 - loss 0.02635219 - time (sec): 33.95 - samples/sec: 1514.47 - lr: 0.000024 - momentum: 0.000000
+2023-10-23 20:59:55,967 epoch 6 - iter 623/894 - loss 0.02640742 - time (sec): 39.47 - samples/sec: 1514.26 - lr: 0.000024 - momentum: 0.000000
+2023-10-23 21:00:01,649 epoch 6 - iter 712/894 - loss 0.02966489 - time (sec): 45.15 - samples/sec: 1521.97 - lr: 0.000023 - momentum: 0.000000
+2023-10-23 21:00:07,488 epoch 6 - iter 801/894 - loss 0.02907114 - time (sec): 50.99 - samples/sec: 1516.15 - lr: 0.000023 - momentum: 0.000000
+2023-10-23 21:00:13,087 epoch 6 - iter 890/894 - loss 0.02979063 - time (sec): 56.59 - samples/sec: 1523.94 - lr: 0.000022 - momentum: 0.000000
+2023-10-23 21:00:13,331 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:00:13,331 EPOCH 6 done: loss 0.0298 - lr: 0.000022
+2023-10-23 21:00:19,831 DEV : loss 0.25447967648506165 - f1-score (micro avg)  0.7468
+2023-10-23 21:00:19,852 saving best model
+2023-10-23 21:00:20,442 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:00:26,004 epoch 7 - iter 89/894 - loss 0.02097532 - time (sec): 5.56 - samples/sec: 1524.38 - lr: 0.000022 - momentum: 0.000000
+2023-10-23 21:00:31,783 epoch 7 - iter 178/894 - loss 0.02109630 - time (sec): 11.34 - samples/sec: 1519.21 - lr: 0.000021 - momentum: 0.000000
+2023-10-23 21:00:37,788 epoch 7 - iter 267/894 - loss 0.01994670 - time (sec): 17.35 - samples/sec: 1536.45 - lr: 0.000021 - momentum: 0.000000
+2023-10-23 21:00:43,398 epoch 7 - iter 356/894 - loss 0.01812653 - time (sec): 22.96 - samples/sec: 1528.07 - lr: 0.000020 - momentum: 0.000000
+2023-10-23 21:00:49,036 epoch 7 - iter 445/894 - loss 0.01965635 - time (sec): 28.59 - samples/sec: 1522.92 - lr: 0.000019 - momentum: 0.000000
+2023-10-23 21:00:54,701 epoch 7 - iter 534/894 - loss 0.01998244 - time (sec): 34.26 - samples/sec: 1526.54 - lr: 0.000019 - momentum: 0.000000
+2023-10-23 21:01:00,374 epoch 7 - iter 623/894 - loss 0.02031292 - time (sec): 39.93 - samples/sec: 1523.49 - lr: 0.000018 - momentum: 0.000000
+2023-10-23 21:01:05,941 epoch 7 - iter 712/894 - loss 0.01882461 - time (sec): 45.50 - samples/sec: 1520.45 - lr: 0.000018 - momentum: 0.000000
+2023-10-23 21:01:11,509 epoch 7 - iter 801/894 - loss 0.02001490 - time (sec): 51.07 - samples/sec: 1523.08 - lr: 0.000017 - momentum: 0.000000
+2023-10-23 21:01:17,109 epoch 7 - iter 890/894 - loss 0.01945576 - time (sec): 56.67 - samples/sec: 1521.90 - lr: 0.000017 - momentum: 0.000000
+2023-10-23 21:01:17,349 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:01:17,350 EPOCH 7 done: loss 0.0197 - lr: 0.000017
+2023-10-23 21:01:23,819 DEV : loss 0.27903473377227783 - f1-score (micro avg)  0.744
+2023-10-23 21:01:23,840 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:01:29,442 epoch 8 - iter 89/894 - loss 0.01477492 - time (sec): 5.60 - samples/sec: 1514.72 - lr: 0.000016 - momentum: 0.000000
+2023-10-23 21:01:35,014 epoch 8 - iter 178/894 - loss 0.01911420 - time (sec): 11.17 - samples/sec: 1524.00 - lr: 0.000016 - momentum: 0.000000
+2023-10-23 21:01:40,581 epoch 8 - iter 267/894 - loss 0.01561106 - time (sec): 16.74 - samples/sec: 1490.26 - lr: 0.000015 - momentum: 0.000000
+2023-10-23 21:01:46,683 epoch 8 - iter 356/894 - loss 0.01289383 - time (sec): 22.84 - samples/sec: 1535.64 - lr: 0.000014 - momentum: 0.000000
+2023-10-23 21:01:52,319 epoch 8 - iter 445/894 - loss 0.01328556 - time (sec): 28.48 - samples/sec: 1539.25 - lr: 0.000014 - momentum: 0.000000
+2023-10-23 21:01:57,972 epoch 8 - iter 534/894 - loss 0.01205554 - time (sec): 34.13 - samples/sec: 1518.84 - lr: 0.000013 - momentum: 0.000000
+2023-10-23 21:02:03,588 epoch 8 - iter 623/894 - loss 0.01126584 - time (sec): 39.75 - samples/sec: 1517.09 - lr: 0.000013 - momentum: 0.000000
+2023-10-23 21:02:09,239 epoch 8 - iter 712/894 - loss 0.01248566 - time (sec): 45.40 - samples/sec: 1515.56 - lr: 0.000012 - momentum: 0.000000
+2023-10-23 21:02:15,129 epoch 8 - iter 801/894 - loss 0.01195343 - time (sec): 51.29 - samples/sec: 1520.84 - lr: 0.000012 - momentum: 0.000000
+2023-10-23 21:02:20,671 epoch 8 - iter 890/894 - loss 0.01193844 - time (sec): 56.83 - samples/sec: 1517.08 - lr: 0.000011 - momentum: 0.000000
+2023-10-23 21:02:20,912 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:02:20,912 EPOCH 8 done: loss 0.0123 - lr: 0.000011
+2023-10-23 21:02:27,403 DEV : loss 0.31139957904815674 - f1-score (micro avg)  0.7589
+2023-10-23 21:02:27,424 saving best model
+2023-10-23 21:02:28,018 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:02:33,491 epoch 9 - iter 89/894 - loss 0.00404374 - time (sec): 5.47 - samples/sec: 1479.01 - lr: 0.000011 - momentum: 0.000000
+2023-10-23 21:02:39,146 epoch 9 - iter 178/894 - loss 0.00808564 - time (sec): 11.13 - samples/sec: 1479.90 - lr: 0.000010 - momentum: 0.000000
+2023-10-23 21:02:44,983 epoch 9 - iter 267/894 - loss 0.00904128 - time (sec): 16.96 - samples/sec: 1498.79 - lr: 0.000009 - momentum: 0.000000
+2023-10-23 21:02:50,610 epoch 9 - iter 356/894 - loss 0.00830892 - time (sec): 22.59 - samples/sec: 1509.23 - lr: 0.000009 - momentum: 0.000000
+2023-10-23 21:02:56,263 epoch 9 - iter 445/894 - loss 0.00809236 - time (sec): 28.24 - samples/sec: 1519.59 - lr: 0.000008 - momentum: 0.000000
+2023-10-23 21:03:02,035 epoch 9 - iter 534/894 - loss 0.00805290 - time (sec): 34.02 - samples/sec: 1522.78 - lr: 0.000008 - momentum: 0.000000
+2023-10-23 21:03:07,916 epoch 9 - iter 623/894 - loss 0.00765601 - time (sec): 39.90 - samples/sec: 1532.31 - lr: 0.000007 - momentum: 0.000000
+2023-10-23 21:03:13,497 epoch 9 - iter 712/894 - loss 0.00744532 - time (sec): 45.48 - samples/sec: 1524.91 - lr: 0.000007 - momentum: 0.000000
+2023-10-23 21:03:18,999 epoch 9 - iter 801/894 - loss 0.00757061 - time (sec): 50.98 - samples/sec: 1522.42 - lr: 0.000006 - momentum: 0.000000
+2023-10-23 21:03:24,708 epoch 9 - iter 890/894 - loss 0.00716724 - time (sec): 56.69 - samples/sec: 1521.97 - lr: 0.000006 - momentum: 0.000000
+2023-10-23 21:03:24,937 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:03:24,938 EPOCH 9 done: loss 0.0071 - lr: 0.000006
+2023-10-23 21:03:31,158 DEV : loss 0.2947549819946289 - f1-score (micro avg)  0.772
+2023-10-23 21:03:31,178 saving best model
+2023-10-23 21:03:31,770 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:03:37,625 epoch 10 - iter 89/894 - loss 0.00103907 - time (sec): 5.85 - samples/sec: 1472.22 - lr: 0.000005 - momentum: 0.000000
+2023-10-23 21:03:43,366 epoch 10 - iter 178/894 - loss 0.00117928 - time (sec): 11.60 - samples/sec: 1525.80 - lr: 0.000004 - momentum: 0.000000
+2023-10-23 21:03:48,985 epoch 10 - iter 267/894 - loss 0.00126812 - time (sec): 17.21 - samples/sec: 1511.46 - lr: 0.000004 - momentum: 0.000000
+2023-10-23 21:03:54,482 epoch 10 - iter 356/894 - loss 0.00168602 - time (sec): 22.71 - samples/sec: 1511.69 - lr: 0.000003 - momentum: 0.000000
+2023-10-23 21:04:00,365 epoch 10 - iter 445/894 - loss 0.00234417 - time (sec): 28.59 - samples/sec: 1530.30 - lr: 0.000003 - momentum: 0.000000
+2023-10-23 21:04:05,924 epoch 10 - iter 534/894 - loss 0.00256521 - time (sec): 34.15 - samples/sec: 1513.63 - lr: 0.000002 - momentum: 0.000000
+2023-10-23 21:04:11,476 epoch 10 - iter 623/894 - loss 0.00250174 - time (sec): 39.71 - samples/sec: 1518.09 - lr: 0.000002 - momentum: 0.000000
+2023-10-23 21:04:17,189 epoch 10 - iter 712/894 - loss 0.00262420 - time (sec): 45.42 - samples/sec: 1515.93 - lr: 0.000001 - momentum: 0.000000
+2023-10-23 21:04:23,075 epoch 10 - iter 801/894 - loss 0.00338086 - time (sec): 51.30 - samples/sec: 1513.04 - lr: 0.000001 - momentum: 0.000000
+2023-10-23 21:04:28,776 epoch 10 - iter 890/894 - loss 0.00333224 - time (sec): 57.01 - samples/sec: 1511.84 - lr: 0.000000 - momentum: 0.000000
+2023-10-23 21:04:29,013 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:04:29,013 EPOCH 10 done: loss 0.0033 - lr: 0.000000
+2023-10-23 21:04:35,263 DEV : loss 0.3027936816215515 - f1-score (micro avg)  0.7733
+2023-10-23 21:04:35,284 saving best model
+2023-10-23 21:04:36,353 ----------------------------------------------------------------------------------------------------
+2023-10-23 21:04:36,354 Loading model from best epoch ...
+2023-10-23 21:04:38,053 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
+2023-10-23 21:04:42,902 
+Results:
+- F-score (micro) 0.7427
+- F-score (macro) 0.6605
+- Accuracy 0.6064
+
+By class:
+              precision    recall  f1-score   support
+
+         loc     0.7984    0.8507    0.8237       596
+        pers     0.6863    0.7688    0.7252       333
+         org     0.5385    0.4773    0.5060       132
+        prod     0.5818    0.4848    0.5289        66
+        time     0.6852    0.7551    0.7184        49
+
+   micro avg     0.7253    0.7611    0.7427      1176
+   macro avg     0.6580    0.6673    0.6605      1176
+weighted avg     0.7206    0.7611    0.7392      1176
+
+2023-10-23 21:04:42,902 ----------------------------------------------------------------------------------------------------