Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,503 @@
+2023-10-25 08:56:05,291 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 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 08:56:05,292 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 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 08:56:05,292 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 Train:  14465 sentences
+2023-10-25 08:56:05,292         (train_with_dev=False, train_with_test=False)
+2023-10-25 08:56:05,292 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 Training Params:
+2023-10-25 08:56:05,292  - learning_rate: "3e-05" 
+2023-10-25 08:56:05,292  - mini_batch_size: "4"
+2023-10-25 08:56:05,292  - max_epochs: "10"
+2023-10-25 08:56:05,292  - shuffle: "True"
+2023-10-25 08:56:05,292 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 Plugins:
+2023-10-25 08:56:05,292  - TensorboardLogger
+2023-10-25 08:56:05,292  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-25 08:56:05,292 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 Final evaluation on model from best epoch (best-model.pt)
+2023-10-25 08:56:05,292  - metric: "('micro avg', 'f1-score')"
+2023-10-25 08:56:05,292 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 Computation:
+2023-10-25 08:56:05,292  - compute on device: cuda:0
+2023-10-25 08:56:05,292  - embedding storage: none
+2023-10-25 08:56:05,292 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,292 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
+2023-10-25 08:56:05,293 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,293 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:56:05,293 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-25 08:56:27,757 epoch 1 - iter 361/3617 - loss 1.29876432 - time (sec): 22.46 - samples/sec: 1685.27 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 08:56:50,077 epoch 1 - iter 722/3617 - loss 0.75385707 - time (sec): 44.78 - samples/sec: 1679.34 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 08:57:12,715 epoch 1 - iter 1083/3617 - loss 0.54794241 - time (sec): 67.42 - samples/sec: 1685.85 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 08:57:35,339 epoch 1 - iter 1444/3617 - loss 0.44521586 - time (sec): 90.05 - samples/sec: 1685.05 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 08:57:57,806 epoch 1 - iter 1805/3617 - loss 0.38171890 - time (sec): 112.51 - samples/sec: 1680.63 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 08:58:20,893 epoch 1 - iter 2166/3617 - loss 0.33646336 - time (sec): 135.60 - samples/sec: 1675.78 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 08:58:43,512 epoch 1 - iter 2527/3617 - loss 0.30293723 - time (sec): 158.22 - samples/sec: 1678.77 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 08:59:06,150 epoch 1 - iter 2888/3617 - loss 0.27974922 - time (sec): 180.86 - samples/sec: 1676.54 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 08:59:28,993 epoch 1 - iter 3249/3617 - loss 0.26111850 - time (sec): 203.70 - samples/sec: 1675.74 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 08:59:51,479 epoch 1 - iter 3610/3617 - loss 0.24710193 - time (sec): 226.19 - samples/sec: 1675.77 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 08:59:51,943 ----------------------------------------------------------------------------------------------------
+2023-10-25 08:59:51,944 EPOCH 1 done: loss 0.2467 - lr: 0.000030
+2023-10-25 08:59:56,474 DEV : loss 0.14493782818317413 - f1-score (micro avg)  0.5921
+2023-10-25 08:59:56,496 saving best model
+2023-10-25 08:59:56,967 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:00:19,557 epoch 2 - iter 361/3617 - loss 0.09481662 - time (sec): 22.59 - samples/sec: 1695.11 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 09:00:42,519 epoch 2 - iter 722/3617 - loss 0.10727292 - time (sec): 45.55 - samples/sec: 1694.09 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 09:01:05,260 epoch 2 - iter 1083/3617 - loss 0.10816822 - time (sec): 68.29 - samples/sec: 1694.24 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 09:01:27,920 epoch 2 - iter 1444/3617 - loss 0.10358701 - time (sec): 90.95 - samples/sec: 1688.21 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 09:01:50,585 epoch 2 - iter 1805/3617 - loss 0.10315773 - time (sec): 113.62 - samples/sec: 1685.42 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 09:02:13,160 epoch 2 - iter 2166/3617 - loss 0.10157426 - time (sec): 136.19 - samples/sec: 1679.24 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 09:02:35,597 epoch 2 - iter 2527/3617 - loss 0.10001100 - time (sec): 158.63 - samples/sec: 1675.89 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 09:02:58,307 epoch 2 - iter 2888/3617 - loss 0.09732052 - time (sec): 181.34 - samples/sec: 1677.76 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 09:03:21,029 epoch 2 - iter 3249/3617 - loss 0.09809576 - time (sec): 204.06 - samples/sec: 1675.59 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 09:03:43,417 epoch 2 - iter 3610/3617 - loss 0.09810723 - time (sec): 226.45 - samples/sec: 1674.16 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 09:03:43,852 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:03:43,852 EPOCH 2 done: loss 0.0980 - lr: 0.000027
+2023-10-25 09:03:49,086 DEV : loss 0.1498355269432068 - f1-score (micro avg)  0.6537
+2023-10-25 09:03:49,108 saving best model
+2023-10-25 09:03:49,728 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:04:12,340 epoch 3 - iter 361/3617 - loss 0.08371286 - time (sec): 22.61 - samples/sec: 1661.67 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 09:04:35,198 epoch 3 - iter 722/3617 - loss 0.08266269 - time (sec): 45.47 - samples/sec: 1671.47 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 09:04:57,535 epoch 3 - iter 1083/3617 - loss 0.07533014 - time (sec): 67.81 - samples/sec: 1676.54 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 09:05:20,055 epoch 3 - iter 1444/3617 - loss 0.07921444 - time (sec): 90.33 - samples/sec: 1672.99 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 09:05:42,693 epoch 3 - iter 1805/3617 - loss 0.07689623 - time (sec): 112.96 - samples/sec: 1679.89 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 09:06:05,757 epoch 3 - iter 2166/3617 - loss 0.07594405 - time (sec): 136.03 - samples/sec: 1684.69 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 09:06:28,208 epoch 3 - iter 2527/3617 - loss 0.07505941 - time (sec): 158.48 - samples/sec: 1678.13 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 09:06:51,076 epoch 3 - iter 2888/3617 - loss 0.07488029 - time (sec): 181.35 - samples/sec: 1685.62 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 09:07:13,857 epoch 3 - iter 3249/3617 - loss 0.07618760 - time (sec): 204.13 - samples/sec: 1680.18 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 09:07:36,286 epoch 3 - iter 3610/3617 - loss 0.07650149 - time (sec): 226.56 - samples/sec: 1674.18 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 09:07:36,709 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:07:36,709 EPOCH 3 done: loss 0.0764 - lr: 0.000023
+2023-10-25 09:07:41,464 DEV : loss 0.19308863580226898 - f1-score (micro avg)  0.6209
+2023-10-25 09:07:41,486 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:08:04,147 epoch 4 - iter 361/3617 - loss 0.04740247 - time (sec): 22.66 - samples/sec: 1676.03 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 09:08:27,052 epoch 4 - iter 722/3617 - loss 0.04393513 - time (sec): 45.57 - samples/sec: 1694.68 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 09:08:49,468 epoch 4 - iter 1083/3617 - loss 0.04673719 - time (sec): 67.98 - samples/sec: 1670.64 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 09:09:12,096 epoch 4 - iter 1444/3617 - loss 0.04771808 - time (sec): 90.61 - samples/sec: 1670.66 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 09:09:34,752 epoch 4 - iter 1805/3617 - loss 0.04805421 - time (sec): 113.27 - samples/sec: 1672.54 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 09:09:57,527 epoch 4 - iter 2166/3617 - loss 0.04811747 - time (sec): 136.04 - samples/sec: 1675.32 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 09:10:20,097 epoch 4 - iter 2527/3617 - loss 0.04985558 - time (sec): 158.61 - samples/sec: 1672.88 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 09:10:43,113 epoch 4 - iter 2888/3617 - loss 0.04967931 - time (sec): 181.63 - samples/sec: 1666.35 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 09:11:05,900 epoch 4 - iter 3249/3617 - loss 0.04983072 - time (sec): 204.41 - samples/sec: 1665.34 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 09:11:28,853 epoch 4 - iter 3610/3617 - loss 0.05188277 - time (sec): 227.37 - samples/sec: 1667.33 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 09:11:29,293 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:11:29,293 EPOCH 4 done: loss 0.0518 - lr: 0.000020
+2023-10-25 09:11:34,065 DEV : loss 0.25538942217826843 - f1-score (micro avg)  0.6376
+2023-10-25 09:11:34,087 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:11:56,512 epoch 5 - iter 361/3617 - loss 0.03131284 - time (sec): 22.42 - samples/sec: 1629.91 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 09:12:19,313 epoch 5 - iter 722/3617 - loss 0.03223206 - time (sec): 45.22 - samples/sec: 1639.25 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 09:12:42,036 epoch 5 - iter 1083/3617 - loss 0.03088082 - time (sec): 67.95 - samples/sec: 1652.27 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 09:13:04,677 epoch 5 - iter 1444/3617 - loss 0.03409690 - time (sec): 90.59 - samples/sec: 1655.84 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 09:13:27,356 epoch 5 - iter 1805/3617 - loss 0.03218071 - time (sec): 113.27 - samples/sec: 1668.62 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 09:13:49,986 epoch 5 - iter 2166/3617 - loss 0.03391101 - time (sec): 135.90 - samples/sec: 1665.03 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 09:14:12,624 epoch 5 - iter 2527/3617 - loss 0.03493067 - time (sec): 158.54 - samples/sec: 1662.52 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 09:14:35,385 epoch 5 - iter 2888/3617 - loss 0.03495628 - time (sec): 181.30 - samples/sec: 1670.98 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 09:14:58,001 epoch 5 - iter 3249/3617 - loss 0.03497871 - time (sec): 203.91 - samples/sec: 1670.29 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 09:15:20,904 epoch 5 - iter 3610/3617 - loss 0.03564780 - time (sec): 226.82 - samples/sec: 1672.37 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 09:15:21,319 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:15:21,319 EPOCH 5 done: loss 0.0357 - lr: 0.000017
+2023-10-25 09:15:26,608 DEV : loss 0.3036385476589203 - f1-score (micro avg)  0.6379
+2023-10-25 09:15:26,630 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:15:49,295 epoch 6 - iter 361/3617 - loss 0.01822029 - time (sec): 22.66 - samples/sec: 1605.12 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 09:16:12,087 epoch 6 - iter 722/3617 - loss 0.02217639 - time (sec): 45.46 - samples/sec: 1662.06 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 09:16:34,918 epoch 6 - iter 1083/3617 - loss 0.02506345 - time (sec): 68.29 - samples/sec: 1664.01 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 09:16:57,390 epoch 6 - iter 1444/3617 - loss 0.02414606 - time (sec): 90.76 - samples/sec: 1655.24 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 09:17:20,050 epoch 6 - iter 1805/3617 - loss 0.02424517 - time (sec): 113.42 - samples/sec: 1662.94 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 09:17:42,507 epoch 6 - iter 2166/3617 - loss 0.02407469 - time (sec): 135.88 - samples/sec: 1663.03 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 09:18:05,243 epoch 6 - iter 2527/3617 - loss 0.02329897 - time (sec): 158.61 - samples/sec: 1665.13 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 09:18:28,017 epoch 6 - iter 2888/3617 - loss 0.02317000 - time (sec): 181.39 - samples/sec: 1670.08 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 09:18:50,676 epoch 6 - iter 3249/3617 - loss 0.02253595 - time (sec): 204.04 - samples/sec: 1670.18 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 09:19:13,356 epoch 6 - iter 3610/3617 - loss 0.02298512 - time (sec): 226.73 - samples/sec: 1671.45 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 09:19:13,810 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:19:13,810 EPOCH 6 done: loss 0.0230 - lr: 0.000013
+2023-10-25 09:19:19,090 DEV : loss 0.3258330523967743 - f1-score (micro avg)  0.6394
+2023-10-25 09:19:19,113 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:19:41,742 epoch 7 - iter 361/3617 - loss 0.01238420 - time (sec): 22.63 - samples/sec: 1691.85 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 09:20:04,086 epoch 7 - iter 722/3617 - loss 0.01141601 - time (sec): 44.97 - samples/sec: 1678.52 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 09:20:26,635 epoch 7 - iter 1083/3617 - loss 0.01410956 - time (sec): 67.52 - samples/sec: 1670.11 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 09:20:49,285 epoch 7 - iter 1444/3617 - loss 0.01436451 - time (sec): 90.17 - samples/sec: 1676.14 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 09:21:12,335 epoch 7 - iter 1805/3617 - loss 0.01504339 - time (sec): 113.22 - samples/sec: 1693.17 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 09:21:34,746 epoch 7 - iter 2166/3617 - loss 0.01505583 - time (sec): 135.63 - samples/sec: 1683.15 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 09:21:57,667 epoch 7 - iter 2527/3617 - loss 0.01548792 - time (sec): 158.55 - samples/sec: 1678.86 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 09:22:20,310 epoch 7 - iter 2888/3617 - loss 0.01540908 - time (sec): 181.20 - samples/sec: 1677.51 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 09:22:43,073 epoch 7 - iter 3249/3617 - loss 0.01583643 - time (sec): 203.96 - samples/sec: 1679.41 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 09:23:05,722 epoch 7 - iter 3610/3617 - loss 0.01543481 - time (sec): 226.61 - samples/sec: 1673.87 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 09:23:06,127 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:23:06,128 EPOCH 7 done: loss 0.0155 - lr: 0.000010
+2023-10-25 09:23:10,894 DEV : loss 0.3687475621700287 - f1-score (micro avg)  0.6512
+2023-10-25 09:23:10,917 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:23:34,320 epoch 8 - iter 361/3617 - loss 0.01011873 - time (sec): 23.40 - samples/sec: 1642.59 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 09:23:57,093 epoch 8 - iter 722/3617 - loss 0.01183084 - time (sec): 46.18 - samples/sec: 1647.32 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 09:24:19,987 epoch 8 - iter 1083/3617 - loss 0.01114849 - time (sec): 69.07 - samples/sec: 1675.33 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 09:24:42,267 epoch 8 - iter 1444/3617 - loss 0.01144658 - time (sec): 91.35 - samples/sec: 1671.61 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 09:25:04,971 epoch 8 - iter 1805/3617 - loss 0.01085694 - time (sec): 114.05 - samples/sec: 1671.04 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 09:25:27,776 epoch 8 - iter 2166/3617 - loss 0.01113943 - time (sec): 136.86 - samples/sec: 1670.33 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 09:25:50,272 epoch 8 - iter 2527/3617 - loss 0.01110272 - time (sec): 159.35 - samples/sec: 1665.95 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 09:26:13,117 epoch 8 - iter 2888/3617 - loss 0.01112695 - time (sec): 182.20 - samples/sec: 1667.86 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 09:26:35,738 epoch 8 - iter 3249/3617 - loss 0.01071467 - time (sec): 204.82 - samples/sec: 1667.74 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 09:26:58,274 epoch 8 - iter 3610/3617 - loss 0.01074639 - time (sec): 227.36 - samples/sec: 1668.14 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 09:26:58,691 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:26:58,691 EPOCH 8 done: loss 0.0107 - lr: 0.000007
+2023-10-25 09:27:03,463 DEV : loss 0.38349881768226624 - f1-score (micro avg)  0.6433
+2023-10-25 09:27:03,486 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:27:26,470 epoch 9 - iter 361/3617 - loss 0.00556864 - time (sec): 22.98 - samples/sec: 1698.80 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 09:27:49,214 epoch 9 - iter 722/3617 - loss 0.00783730 - time (sec): 45.73 - samples/sec: 1713.36 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 09:28:11,732 epoch 9 - iter 1083/3617 - loss 0.00688603 - time (sec): 68.25 - samples/sec: 1699.80 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 09:28:34,228 epoch 9 - iter 1444/3617 - loss 0.00661452 - time (sec): 90.74 - samples/sec: 1681.63 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 09:28:57,185 epoch 9 - iter 1805/3617 - loss 0.00671017 - time (sec): 113.70 - samples/sec: 1690.74 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 09:29:19,774 epoch 9 - iter 2166/3617 - loss 0.00667753 - time (sec): 136.29 - samples/sec: 1681.32 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 09:29:42,402 epoch 9 - iter 2527/3617 - loss 0.00799751 - time (sec): 158.92 - samples/sec: 1675.07 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 09:30:05,056 epoch 9 - iter 2888/3617 - loss 0.00813035 - time (sec): 181.57 - samples/sec: 1675.38 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 09:30:28,208 epoch 9 - iter 3249/3617 - loss 0.00804585 - time (sec): 204.72 - samples/sec: 1670.75 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 09:30:50,683 epoch 9 - iter 3610/3617 - loss 0.00784812 - time (sec): 227.20 - samples/sec: 1668.02 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 09:30:51,156 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:30:51,156 EPOCH 9 done: loss 0.0079 - lr: 0.000003
+2023-10-25 09:30:55,937 DEV : loss 0.3988388478755951 - f1-score (micro avg)  0.6402
+2023-10-25 09:30:55,959 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:31:18,550 epoch 10 - iter 361/3617 - loss 0.00169395 - time (sec): 22.59 - samples/sec: 1691.67 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 09:31:41,128 epoch 10 - iter 722/3617 - loss 0.00257176 - time (sec): 45.17 - samples/sec: 1691.41 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 09:32:03,905 epoch 10 - iter 1083/3617 - loss 0.00388498 - time (sec): 67.95 - samples/sec: 1670.61 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 09:32:26,672 epoch 10 - iter 1444/3617 - loss 0.00415693 - time (sec): 90.71 - samples/sec: 1674.51 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 09:32:49,198 epoch 10 - iter 1805/3617 - loss 0.00422595 - time (sec): 113.24 - samples/sec: 1665.99 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 09:33:11,815 epoch 10 - iter 2166/3617 - loss 0.00444188 - time (sec): 135.86 - samples/sec: 1665.22 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 09:33:34,466 epoch 10 - iter 2527/3617 - loss 0.00456308 - time (sec): 158.51 - samples/sec: 1659.07 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 09:33:57,358 epoch 10 - iter 2888/3617 - loss 0.00457433 - time (sec): 181.40 - samples/sec: 1663.72 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 09:34:20,142 epoch 10 - iter 3249/3617 - loss 0.00465404 - time (sec): 204.18 - samples/sec: 1668.71 - lr: 0.000000 - momentum: 0.000000
+2023-10-25 09:34:42,847 epoch 10 - iter 3610/3617 - loss 0.00478068 - time (sec): 226.89 - samples/sec: 1672.23 - lr: 0.000000 - momentum: 0.000000
+2023-10-25 09:34:43,247 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:34:43,247 EPOCH 10 done: loss 0.0048 - lr: 0.000000
+2023-10-25 09:34:48,560 DEV : loss 0.42030808329582214 - f1-score (micro avg)  0.6507
+2023-10-25 09:34:49,057 ----------------------------------------------------------------------------------------------------
+2023-10-25 09:34:49,058 Loading model from best epoch ...
+2023-10-25 09:34:50,737 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 09:34:56,439 
+Results:
+- F-score (micro) 0.6562
+- F-score (macro) 0.4469
+- Accuracy 0.499
+
+By class:
+              precision    recall  f1-score   support
+
+         loc     0.6340    0.8088    0.7108       591
+        pers     0.5688    0.7059    0.6300       357
+         org     0.0000    0.0000    0.0000        79
+
+   micro avg     0.6093    0.7108    0.6562      1027
+   macro avg     0.4009    0.5049    0.4469      1027
+weighted avg     0.5626    0.7108    0.6280      1027
+
+2023-10-25 09:34:56,439 ----------------------------------------------------------------------------------------------------