Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,503 @@
+2023-10-25 17:53:07,735 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,736 Model: "SequenceTagger(
+  (embeddings): TransformerWordEmbeddings(
+    (model): BertModel(
+      (embeddings): BertEmbeddings(
+        (word_embeddings): Embedding(64001, 768)
+        (position_embeddings): Embedding(512, 768)
+        (token_type_embeddings): Embedding(2, 768)
+        (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+        (dropout): Dropout(p=0.1, inplace=False)
+      )
+      (encoder): BertEncoder(
+        (layer): ModuleList(
+          (0): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (1): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (2): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (3): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (4): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (5): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (6): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (7): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (8): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (9): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (10): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+          (11): BertLayer(
+            (attention): BertAttention(
+              (self): BertSelfAttention(
+                (query): Linear(in_features=768, out_features=768, bias=True)
+                (key): Linear(in_features=768, out_features=768, bias=True)
+                (value): Linear(in_features=768, out_features=768, bias=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+              (output): BertSelfOutput(
+                (dense): Linear(in_features=768, out_features=768, bias=True)
+                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+                (dropout): Dropout(p=0.1, inplace=False)
+              )
+            )
+            (intermediate): BertIntermediate(
+              (dense): Linear(in_features=768, out_features=3072, bias=True)
+              (intermediate_act_fn): GELUActivation()
+            )
+            (output): BertOutput(
+              (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
+              (dropout): Dropout(p=0.1, inplace=False)
+            )
+          )
+        )
+      )
+      (pooler): BertPooler(
+        (dense): Linear(in_features=768, out_features=768, bias=True)
+        (activation): Tanh()
+      )
+    )
+  )
+  (locked_dropout): LockedDropout(p=0.5)
+  (linear): Linear(in_features=768, out_features=13, bias=True)
+  (loss_function): CrossEntropyLoss()
+)"
+2023-10-25 17:53:07,736 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,736 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
+2023-10-25 17:53:07,736 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,736 Train:  14465 sentences
+2023-10-25 17:53:07,736         (train_with_dev=False, train_with_test=False)
+2023-10-25 17:53:07,736 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,736 Training Params:
+2023-10-25 17:53:07,736  - learning_rate: "3e-05" 
+2023-10-25 17:53:07,736  - mini_batch_size: "4"
+2023-10-25 17:53:07,736  - max_epochs: "10"
+2023-10-25 17:53:07,736  - shuffle: "True"
+2023-10-25 17:53:07,736 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,737 Plugins:
+2023-10-25 17:53:07,737  - TensorboardLogger
+2023-10-25 17:53:07,737  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-25 17:53:07,737 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,737 Final evaluation on model from best epoch (best-model.pt)
+2023-10-25 17:53:07,737  - metric: "('micro avg', 'f1-score')"
+2023-10-25 17:53:07,737 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,737 Computation:
+2023-10-25 17:53:07,737  - compute on device: cuda:0
+2023-10-25 17:53:07,737  - embedding storage: none
+2023-10-25 17:53:07,737 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,737 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
+2023-10-25 17:53:07,737 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,737 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:53:07,737 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-25 17:53:30,177 epoch 1 - iter 361/3617 - loss 1.04448431 - time (sec): 22.44 - samples/sec: 1725.27 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 17:53:52,736 epoch 1 - iter 722/3617 - loss 0.62986808 - time (sec): 45.00 - samples/sec: 1706.63 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 17:54:15,328 epoch 1 - iter 1083/3617 - loss 0.47556906 - time (sec): 67.59 - samples/sec: 1695.64 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 17:54:37,780 epoch 1 - iter 1444/3617 - loss 0.39046577 - time (sec): 90.04 - samples/sec: 1697.01 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 17:55:00,290 epoch 1 - iter 1805/3617 - loss 0.33554242 - time (sec): 112.55 - samples/sec: 1688.24 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 17:55:22,907 epoch 1 - iter 2166/3617 - loss 0.30184490 - time (sec): 135.17 - samples/sec: 1681.32 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 17:55:45,800 epoch 1 - iter 2527/3617 - loss 0.27353951 - time (sec): 158.06 - samples/sec: 1683.62 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 17:56:08,540 epoch 1 - iter 2888/3617 - loss 0.25459014 - time (sec): 180.80 - samples/sec: 1674.95 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 17:56:31,402 epoch 1 - iter 3249/3617 - loss 0.23801927 - time (sec): 203.66 - samples/sec: 1673.95 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 17:56:54,160 epoch 1 - iter 3610/3617 - loss 0.22532715 - time (sec): 226.42 - samples/sec: 1675.31 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 17:56:54,573 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:56:54,573 EPOCH 1 done: loss 0.2251 - lr: 0.000030
+2023-10-25 17:56:59,104 DEV : loss 0.14202608168125153 - f1-score (micro avg)  0.6083
+2023-10-25 17:56:59,127 saving best model
+2023-10-25 17:56:59,676 ----------------------------------------------------------------------------------------------------
+2023-10-25 17:57:22,365 epoch 2 - iter 361/3617 - loss 0.09325387 - time (sec): 22.69 - samples/sec: 1653.93 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 17:57:44,957 epoch 2 - iter 722/3617 - loss 0.09875007 - time (sec): 45.28 - samples/sec: 1653.86 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 17:58:07,620 epoch 2 - iter 1083/3617 - loss 0.09947355 - time (sec): 67.94 - samples/sec: 1662.40 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 17:58:30,191 epoch 2 - iter 1444/3617 - loss 0.10125065 - time (sec): 90.51 - samples/sec: 1665.36 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 17:58:53,134 epoch 2 - iter 1805/3617 - loss 0.10017178 - time (sec): 113.46 - samples/sec: 1680.24 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 17:59:15,812 epoch 2 - iter 2166/3617 - loss 0.10001999 - time (sec): 136.13 - samples/sec: 1678.91 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 17:59:38,412 epoch 2 - iter 2527/3617 - loss 0.09792164 - time (sec): 158.73 - samples/sec: 1676.16 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 18:00:01,213 epoch 2 - iter 2888/3617 - loss 0.09669901 - time (sec): 181.54 - samples/sec: 1675.51 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 18:00:24,017 epoch 2 - iter 3249/3617 - loss 0.09713692 - time (sec): 204.34 - samples/sec: 1674.30 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 18:00:46,631 epoch 2 - iter 3610/3617 - loss 0.09773196 - time (sec): 226.95 - samples/sec: 1671.96 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 18:00:47,034 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:00:47,034 EPOCH 2 done: loss 0.0977 - lr: 0.000027
+2023-10-25 18:00:51,792 DEV : loss 0.14715531468391418 - f1-score (micro avg)  0.6016
+2023-10-25 18:00:51,815 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:01:15,000 epoch 3 - iter 361/3617 - loss 0.06760835 - time (sec): 23.18 - samples/sec: 1667.13 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 18:01:38,218 epoch 3 - iter 722/3617 - loss 0.06991201 - time (sec): 46.40 - samples/sec: 1723.47 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 18:02:00,928 epoch 3 - iter 1083/3617 - loss 0.06632920 - time (sec): 69.11 - samples/sec: 1713.65 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 18:02:23,506 epoch 3 - iter 1444/3617 - loss 0.06914393 - time (sec): 91.69 - samples/sec: 1705.05 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 18:02:45,976 epoch 3 - iter 1805/3617 - loss 0.07123450 - time (sec): 114.16 - samples/sec: 1692.95 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 18:03:08,412 epoch 3 - iter 2166/3617 - loss 0.07224670 - time (sec): 136.60 - samples/sec: 1684.65 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 18:03:30,979 epoch 3 - iter 2527/3617 - loss 0.07309131 - time (sec): 159.16 - samples/sec: 1683.48 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 18:03:53,575 epoch 3 - iter 2888/3617 - loss 0.07511697 - time (sec): 181.76 - samples/sec: 1677.20 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 18:04:16,265 epoch 3 - iter 3249/3617 - loss 0.07486815 - time (sec): 204.45 - samples/sec: 1674.48 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 18:04:38,616 epoch 3 - iter 3610/3617 - loss 0.07515962 - time (sec): 226.80 - samples/sec: 1672.69 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 18:04:39,041 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:04:39,041 EPOCH 3 done: loss 0.0751 - lr: 0.000023
+2023-10-25 18:04:43,797 DEV : loss 0.2039371132850647 - f1-score (micro avg)  0.6501
+2023-10-25 18:04:43,819 saving best model
+2023-10-25 18:04:44,590 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:05:07,373 epoch 4 - iter 361/3617 - loss 0.05450055 - time (sec): 22.78 - samples/sec: 1685.26 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 18:05:29,930 epoch 4 - iter 722/3617 - loss 0.04868394 - time (sec): 45.34 - samples/sec: 1680.30 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 18:05:52,692 epoch 4 - iter 1083/3617 - loss 0.04724397 - time (sec): 68.10 - samples/sec: 1692.84 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 18:06:15,338 epoch 4 - iter 1444/3617 - loss 0.04713960 - time (sec): 90.75 - samples/sec: 1698.77 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 18:06:37,961 epoch 4 - iter 1805/3617 - loss 0.04948343 - time (sec): 113.37 - samples/sec: 1696.17 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 18:07:00,499 epoch 4 - iter 2166/3617 - loss 0.04977775 - time (sec): 135.91 - samples/sec: 1685.63 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 18:07:22,960 epoch 4 - iter 2527/3617 - loss 0.04973117 - time (sec): 158.37 - samples/sec: 1680.12 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 18:07:45,582 epoch 4 - iter 2888/3617 - loss 0.05015542 - time (sec): 180.99 - samples/sec: 1677.24 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 18:08:08,593 epoch 4 - iter 3249/3617 - loss 0.05042575 - time (sec): 204.00 - samples/sec: 1670.53 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 18:08:31,332 epoch 4 - iter 3610/3617 - loss 0.05053351 - time (sec): 226.74 - samples/sec: 1673.42 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 18:08:31,747 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:08:31,748 EPOCH 4 done: loss 0.0507 - lr: 0.000020
+2023-10-25 18:08:36,510 DEV : loss 0.24384552240371704 - f1-score (micro avg)  0.6139
+2023-10-25 18:08:36,532 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:08:59,252 epoch 5 - iter 361/3617 - loss 0.03078975 - time (sec): 22.72 - samples/sec: 1723.25 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 18:09:22,026 epoch 5 - iter 722/3617 - loss 0.03379188 - time (sec): 45.49 - samples/sec: 1704.90 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 18:09:44,670 epoch 5 - iter 1083/3617 - loss 0.03494238 - time (sec): 68.14 - samples/sec: 1697.74 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 18:10:06,931 epoch 5 - iter 1444/3617 - loss 0.03589940 - time (sec): 90.40 - samples/sec: 1670.73 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 18:10:29,820 epoch 5 - iter 1805/3617 - loss 0.03741139 - time (sec): 113.29 - samples/sec: 1679.50 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 18:10:52,691 epoch 5 - iter 2166/3617 - loss 0.03745558 - time (sec): 136.16 - samples/sec: 1683.12 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 18:11:15,175 epoch 5 - iter 2527/3617 - loss 0.03750218 - time (sec): 158.64 - samples/sec: 1674.48 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 18:11:37,722 epoch 5 - iter 2888/3617 - loss 0.03678568 - time (sec): 181.19 - samples/sec: 1672.19 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 18:12:00,225 epoch 5 - iter 3249/3617 - loss 0.03673079 - time (sec): 203.69 - samples/sec: 1666.92 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 18:12:23,199 epoch 5 - iter 3610/3617 - loss 0.03582200 - time (sec): 226.67 - samples/sec: 1674.22 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 18:12:23,601 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:12:23,601 EPOCH 5 done: loss 0.0358 - lr: 0.000017
+2023-10-25 18:12:28,874 DEV : loss 0.29047203063964844 - f1-score (micro avg)  0.6375
+2023-10-25 18:12:28,897 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:12:51,381 epoch 6 - iter 361/3617 - loss 0.02612742 - time (sec): 22.48 - samples/sec: 1642.43 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 18:13:13,926 epoch 6 - iter 722/3617 - loss 0.02633927 - time (sec): 45.03 - samples/sec: 1658.37 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 18:13:36,722 epoch 6 - iter 1083/3617 - loss 0.02499591 - time (sec): 67.82 - samples/sec: 1674.19 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 18:13:59,270 epoch 6 - iter 1444/3617 - loss 0.02561653 - time (sec): 90.37 - samples/sec: 1675.88 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 18:14:22,086 epoch 6 - iter 1805/3617 - loss 0.02554121 - time (sec): 113.19 - samples/sec: 1672.16 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 18:14:44,503 epoch 6 - iter 2166/3617 - loss 0.02594605 - time (sec): 135.61 - samples/sec: 1667.09 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 18:15:06,952 epoch 6 - iter 2527/3617 - loss 0.02566906 - time (sec): 158.05 - samples/sec: 1662.64 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 18:15:29,691 epoch 6 - iter 2888/3617 - loss 0.02638375 - time (sec): 180.79 - samples/sec: 1669.32 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 18:15:52,576 epoch 6 - iter 3249/3617 - loss 0.02624045 - time (sec): 203.68 - samples/sec: 1673.50 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 18:16:15,346 epoch 6 - iter 3610/3617 - loss 0.02618026 - time (sec): 226.45 - samples/sec: 1674.81 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 18:16:15,770 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:16:15,771 EPOCH 6 done: loss 0.0261 - lr: 0.000013
+2023-10-25 18:16:21,044 DEV : loss 0.35754987597465515 - f1-score (micro avg)  0.6486
+2023-10-25 18:16:21,067 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:16:43,741 epoch 7 - iter 361/3617 - loss 0.02669619 - time (sec): 22.67 - samples/sec: 1694.80 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 18:17:06,457 epoch 7 - iter 722/3617 - loss 0.02133193 - time (sec): 45.39 - samples/sec: 1690.52 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 18:17:29,252 epoch 7 - iter 1083/3617 - loss 0.01919200 - time (sec): 68.18 - samples/sec: 1696.94 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 18:17:51,921 epoch 7 - iter 1444/3617 - loss 0.01837169 - time (sec): 90.85 - samples/sec: 1700.41 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 18:18:14,289 epoch 7 - iter 1805/3617 - loss 0.01828680 - time (sec): 113.22 - samples/sec: 1683.38 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 18:18:36,956 epoch 7 - iter 2166/3617 - loss 0.01791469 - time (sec): 135.89 - samples/sec: 1672.40 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 18:18:59,536 epoch 7 - iter 2527/3617 - loss 0.01755958 - time (sec): 158.47 - samples/sec: 1666.66 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 18:19:22,334 epoch 7 - iter 2888/3617 - loss 0.01737112 - time (sec): 181.27 - samples/sec: 1667.36 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 18:19:44,988 epoch 7 - iter 3249/3617 - loss 0.01742728 - time (sec): 203.92 - samples/sec: 1671.26 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 18:20:07,652 epoch 7 - iter 3610/3617 - loss 0.01735064 - time (sec): 226.58 - samples/sec: 1673.83 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 18:20:08,070 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:20:08,070 EPOCH 7 done: loss 0.0174 - lr: 0.000010
+2023-10-25 18:20:13,372 DEV : loss 0.3536568582057953 - f1-score (micro avg)  0.6385
+2023-10-25 18:20:13,396 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:20:35,975 epoch 8 - iter 361/3617 - loss 0.01206039 - time (sec): 22.58 - samples/sec: 1635.31 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 18:20:58,625 epoch 8 - iter 722/3617 - loss 0.01278203 - time (sec): 45.23 - samples/sec: 1648.62 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 18:21:21,240 epoch 8 - iter 1083/3617 - loss 0.01364976 - time (sec): 67.84 - samples/sec: 1649.06 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 18:21:43,895 epoch 8 - iter 1444/3617 - loss 0.01307669 - time (sec): 90.50 - samples/sec: 1654.06 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 18:22:06,544 epoch 8 - iter 1805/3617 - loss 0.01174791 - time (sec): 113.15 - samples/sec: 1658.98 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 18:22:29,142 epoch 8 - iter 2166/3617 - loss 0.01152362 - time (sec): 135.75 - samples/sec: 1658.48 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 18:22:51,686 epoch 8 - iter 2527/3617 - loss 0.01119897 - time (sec): 158.29 - samples/sec: 1659.80 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 18:23:14,109 epoch 8 - iter 2888/3617 - loss 0.01063586 - time (sec): 180.71 - samples/sec: 1657.02 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 18:23:37,077 epoch 8 - iter 3249/3617 - loss 0.01119434 - time (sec): 203.68 - samples/sec: 1663.50 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 18:24:00,281 epoch 8 - iter 3610/3617 - loss 0.01118139 - time (sec): 226.88 - samples/sec: 1671.90 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 18:24:00,698 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:24:00,698 EPOCH 8 done: loss 0.0112 - lr: 0.000007
+2023-10-25 18:24:06,004 DEV : loss 0.37936946749687195 - f1-score (micro avg)  0.6465
+2023-10-25 18:24:06,027 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:24:28,653 epoch 9 - iter 361/3617 - loss 0.00453700 - time (sec): 22.62 - samples/sec: 1683.71 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 18:24:51,313 epoch 9 - iter 722/3617 - loss 0.00589753 - time (sec): 45.29 - samples/sec: 1687.02 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 18:25:14,005 epoch 9 - iter 1083/3617 - loss 0.00678198 - time (sec): 67.98 - samples/sec: 1685.07 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 18:25:36,711 epoch 9 - iter 1444/3617 - loss 0.00698786 - time (sec): 90.68 - samples/sec: 1676.57 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 18:25:59,553 epoch 9 - iter 1805/3617 - loss 0.00683517 - time (sec): 113.52 - samples/sec: 1676.20 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 18:26:22,155 epoch 9 - iter 2166/3617 - loss 0.00688052 - time (sec): 136.13 - samples/sec: 1673.27 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 18:26:44,919 epoch 9 - iter 2527/3617 - loss 0.00701541 - time (sec): 158.89 - samples/sec: 1669.59 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 18:27:07,409 epoch 9 - iter 2888/3617 - loss 0.00693063 - time (sec): 181.38 - samples/sec: 1666.37 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 18:27:29,896 epoch 9 - iter 3249/3617 - loss 0.00674220 - time (sec): 203.87 - samples/sec: 1666.51 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 18:27:52,714 epoch 9 - iter 3610/3617 - loss 0.00681525 - time (sec): 226.69 - samples/sec: 1672.04 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 18:27:53,186 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:27:53,186 EPOCH 9 done: loss 0.0068 - lr: 0.000003
+2023-10-25 18:27:57,959 DEV : loss 0.41782665252685547 - f1-score (micro avg)  0.6447
+2023-10-25 18:27:57,982 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:28:21,037 epoch 10 - iter 361/3617 - loss 0.00866093 - time (sec): 23.05 - samples/sec: 1651.05 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 18:28:43,699 epoch 10 - iter 722/3617 - loss 0.00532429 - time (sec): 45.72 - samples/sec: 1676.97 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 18:29:06,533 epoch 10 - iter 1083/3617 - loss 0.00622948 - time (sec): 68.55 - samples/sec: 1677.53 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 18:29:29,165 epoch 10 - iter 1444/3617 - loss 0.00568970 - time (sec): 91.18 - samples/sec: 1669.35 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 18:29:51,935 epoch 10 - iter 1805/3617 - loss 0.00558160 - time (sec): 113.95 - samples/sec: 1675.59 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 18:30:14,674 epoch 10 - iter 2166/3617 - loss 0.00514416 - time (sec): 136.69 - samples/sec: 1674.83 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 18:30:37,246 epoch 10 - iter 2527/3617 - loss 0.00503834 - time (sec): 159.26 - samples/sec: 1670.17 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 18:30:59,921 epoch 10 - iter 2888/3617 - loss 0.00495744 - time (sec): 181.94 - samples/sec: 1672.40 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 18:31:22,734 epoch 10 - iter 3249/3617 - loss 0.00479787 - time (sec): 204.75 - samples/sec: 1675.27 - lr: 0.000000 - momentum: 0.000000
+2023-10-25 18:31:45,145 epoch 10 - iter 3610/3617 - loss 0.00477649 - time (sec): 227.16 - samples/sec: 1669.56 - lr: 0.000000 - momentum: 0.000000
+2023-10-25 18:31:45,583 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:31:45,583 EPOCH 10 done: loss 0.0048 - lr: 0.000000
+2023-10-25 18:31:50,356 DEV : loss 0.416111558675766 - f1-score (micro avg)  0.6427
+2023-10-25 18:31:50,932 ----------------------------------------------------------------------------------------------------
+2023-10-25 18:31:50,933 Loading model from best epoch ...
+2023-10-25 18:31:52,701 SequenceTagger predicts: Dictionary with 13 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
+2023-10-25 18:31:58,354 
+Results:
+- F-score (micro) 0.6515
+- F-score (macro) 0.448
+- Accuracy 0.4966
+
+By class:
+              precision    recall  f1-score   support
+
+         loc     0.6294    0.7817    0.6974       591
+        pers     0.5663    0.7535    0.6466       357
+         org     0.0000    0.0000    0.0000        79
+
+   micro avg     0.6007    0.7118    0.6515      1027
+   macro avg     0.3986    0.5117    0.4480      1027
+weighted avg     0.5591    0.7118    0.6261      1027
+
+2023-10-25 18:31:58,354 ----------------------------------------------------------------------------------------------------