Upload ./training.log with huggingface_hub

training.log

@@ -0,0 +1,504 @@
+2023-10-25 12:56:32,932 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,933 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 12:56:32,933 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 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 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 Train:  14465 sentences
+2023-10-25 12:56:32,934         (train_with_dev=False, train_with_test=False)
+2023-10-25 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 Training Params:
+2023-10-25 12:56:32,934  - learning_rate: "5e-05" 
+2023-10-25 12:56:32,934  - mini_batch_size: "8"
+2023-10-25 12:56:32,934  - max_epochs: "10"
+2023-10-25 12:56:32,934  - shuffle: "True"
+2023-10-25 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 Plugins:
+2023-10-25 12:56:32,934  - TensorboardLogger
+2023-10-25 12:56:32,934  - LinearScheduler | warmup_fraction: '0.1'
+2023-10-25 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 Final evaluation on model from best epoch (best-model.pt)
+2023-10-25 12:56:32,934  - metric: "('micro avg', 'f1-score')"
+2023-10-25 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 Computation:
+2023-10-25 12:56:32,934  - compute on device: cuda:0
+2023-10-25 12:56:32,934  - embedding storage: none
+2023-10-25 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
+2023-10-25 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:56:32,934 Logging anything other than scalars to TensorBoard is currently not supported.
+2023-10-25 12:56:48,346 epoch 1 - iter 180/1809 - loss 1.10006084 - time (sec): 15.41 - samples/sec: 2402.62 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 12:57:04,474 epoch 1 - iter 360/1809 - loss 0.63052655 - time (sec): 31.54 - samples/sec: 2436.05 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 12:57:20,154 epoch 1 - iter 540/1809 - loss 0.47100990 - time (sec): 47.22 - samples/sec: 2427.01 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 12:57:35,999 epoch 1 - iter 720/1809 - loss 0.38400724 - time (sec): 63.06 - samples/sec: 2427.43 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 12:57:51,832 epoch 1 - iter 900/1809 - loss 0.33257800 - time (sec): 78.90 - samples/sec: 2412.15 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 12:58:07,695 epoch 1 - iter 1080/1809 - loss 0.29578277 - time (sec): 94.76 - samples/sec: 2405.28 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 12:58:23,282 epoch 1 - iter 1260/1809 - loss 0.26811077 - time (sec): 110.35 - samples/sec: 2407.63 - lr: 0.000035 - momentum: 0.000000
+2023-10-25 12:58:39,159 epoch 1 - iter 1440/1809 - loss 0.24867204 - time (sec): 126.22 - samples/sec: 2401.15 - lr: 0.000040 - momentum: 0.000000
+2023-10-25 12:58:54,972 epoch 1 - iter 1620/1809 - loss 0.23254968 - time (sec): 142.04 - samples/sec: 2394.45 - lr: 0.000045 - momentum: 0.000000
+2023-10-25 12:59:10,963 epoch 1 - iter 1800/1809 - loss 0.21944741 - time (sec): 158.03 - samples/sec: 2393.36 - lr: 0.000050 - momentum: 0.000000
+2023-10-25 12:59:11,727 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:59:11,727 EPOCH 1 done: loss 0.2190 - lr: 0.000050
+2023-10-25 12:59:16,227 DEV : loss 0.0940776988863945 - f1-score (micro avg)  0.5283
+2023-10-25 12:59:16,250 saving best model
+2023-10-25 12:59:16,804 ----------------------------------------------------------------------------------------------------
+2023-10-25 12:59:32,156 epoch 2 - iter 180/1809 - loss 0.07972278 - time (sec): 15.35 - samples/sec: 2377.73 - lr: 0.000049 - momentum: 0.000000
+2023-10-25 12:59:48,323 epoch 2 - iter 360/1809 - loss 0.08152052 - time (sec): 31.52 - samples/sec: 2340.68 - lr: 0.000049 - momentum: 0.000000
+2023-10-25 13:00:04,570 epoch 2 - iter 540/1809 - loss 0.08505170 - time (sec): 47.77 - samples/sec: 2366.58 - lr: 0.000048 - momentum: 0.000000
+2023-10-25 13:00:20,330 epoch 2 - iter 720/1809 - loss 0.08594619 - time (sec): 63.53 - samples/sec: 2376.02 - lr: 0.000048 - momentum: 0.000000
+2023-10-25 13:00:36,207 epoch 2 - iter 900/1809 - loss 0.08806352 - time (sec): 79.40 - samples/sec: 2380.43 - lr: 0.000047 - momentum: 0.000000
+2023-10-25 13:00:51,928 epoch 2 - iter 1080/1809 - loss 0.08857237 - time (sec): 95.12 - samples/sec: 2379.41 - lr: 0.000047 - momentum: 0.000000
+2023-10-25 13:01:07,495 epoch 2 - iter 1260/1809 - loss 0.08718027 - time (sec): 110.69 - samples/sec: 2386.51 - lr: 0.000046 - momentum: 0.000000
+2023-10-25 13:01:23,189 epoch 2 - iter 1440/1809 - loss 0.08666178 - time (sec): 126.38 - samples/sec: 2392.20 - lr: 0.000046 - momentum: 0.000000
+2023-10-25 13:01:38,806 epoch 2 - iter 1620/1809 - loss 0.08537196 - time (sec): 142.00 - samples/sec: 2395.91 - lr: 0.000045 - momentum: 0.000000
+2023-10-25 13:01:55,003 epoch 2 - iter 1800/1809 - loss 0.08624945 - time (sec): 158.20 - samples/sec: 2390.41 - lr: 0.000044 - momentum: 0.000000
+2023-10-25 13:01:55,826 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:01:55,826 EPOCH 2 done: loss 0.0862 - lr: 0.000044
+2023-10-25 13:02:01,076 DEV : loss 0.13432565331459045 - f1-score (micro avg)  0.6025
+2023-10-25 13:02:01,098 saving best model
+2023-10-25 13:02:01,754 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:02:17,323 epoch 3 - iter 180/1809 - loss 0.05779259 - time (sec): 15.57 - samples/sec: 2359.77 - lr: 0.000044 - momentum: 0.000000
+2023-10-25 13:02:33,718 epoch 3 - iter 360/1809 - loss 0.05644142 - time (sec): 31.96 - samples/sec: 2360.99 - lr: 0.000043 - momentum: 0.000000
+2023-10-25 13:02:49,700 epoch 3 - iter 540/1809 - loss 0.06025166 - time (sec): 47.94 - samples/sec: 2376.32 - lr: 0.000043 - momentum: 0.000000
+2023-10-25 13:03:05,515 epoch 3 - iter 720/1809 - loss 0.05963981 - time (sec): 63.76 - samples/sec: 2398.85 - lr: 0.000042 - momentum: 0.000000
+2023-10-25 13:03:21,210 epoch 3 - iter 900/1809 - loss 0.05988365 - time (sec): 79.45 - samples/sec: 2391.83 - lr: 0.000042 - momentum: 0.000000
+2023-10-25 13:03:37,246 epoch 3 - iter 1080/1809 - loss 0.06110576 - time (sec): 95.49 - samples/sec: 2395.55 - lr: 0.000041 - momentum: 0.000000
+2023-10-25 13:03:53,081 epoch 3 - iter 1260/1809 - loss 0.05959679 - time (sec): 111.33 - samples/sec: 2397.88 - lr: 0.000041 - momentum: 0.000000
+2023-10-25 13:04:08,904 epoch 3 - iter 1440/1809 - loss 0.05990670 - time (sec): 127.15 - samples/sec: 2392.99 - lr: 0.000040 - momentum: 0.000000
+2023-10-25 13:04:24,144 epoch 3 - iter 1620/1809 - loss 0.05964992 - time (sec): 142.39 - samples/sec: 2380.45 - lr: 0.000039 - momentum: 0.000000
+2023-10-25 13:04:40,347 epoch 3 - iter 1800/1809 - loss 0.06114775 - time (sec): 158.59 - samples/sec: 2382.72 - lr: 0.000039 - momentum: 0.000000
+2023-10-25 13:04:41,213 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:04:41,213 EPOCH 3 done: loss 0.0611 - lr: 0.000039
+2023-10-25 13:04:46,486 DEV : loss 0.1459859311580658 - f1-score (micro avg)  0.6574
+2023-10-25 13:04:46,509 saving best model
+2023-10-25 13:04:47,256 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:05:03,087 epoch 4 - iter 180/1809 - loss 0.03569500 - time (sec): 15.83 - samples/sec: 2388.59 - lr: 0.000038 - momentum: 0.000000
+2023-10-25 13:05:18,721 epoch 4 - iter 360/1809 - loss 0.03919591 - time (sec): 31.46 - samples/sec: 2389.76 - lr: 0.000038 - momentum: 0.000000
+2023-10-25 13:05:34,881 epoch 4 - iter 540/1809 - loss 0.04102332 - time (sec): 47.62 - samples/sec: 2380.28 - lr: 0.000037 - momentum: 0.000000
+2023-10-25 13:05:50,661 epoch 4 - iter 720/1809 - loss 0.04009188 - time (sec): 63.40 - samples/sec: 2377.07 - lr: 0.000037 - momentum: 0.000000
+2023-10-25 13:06:06,635 epoch 4 - iter 900/1809 - loss 0.04101052 - time (sec): 79.38 - samples/sec: 2383.76 - lr: 0.000036 - momentum: 0.000000
+2023-10-25 13:06:22,324 epoch 4 - iter 1080/1809 - loss 0.04250899 - time (sec): 95.07 - samples/sec: 2389.95 - lr: 0.000036 - momentum: 0.000000
+2023-10-25 13:06:37,963 epoch 4 - iter 1260/1809 - loss 0.04333909 - time (sec): 110.71 - samples/sec: 2386.49 - lr: 0.000035 - momentum: 0.000000
+2023-10-25 13:06:53,854 epoch 4 - iter 1440/1809 - loss 0.04374822 - time (sec): 126.60 - samples/sec: 2380.16 - lr: 0.000034 - momentum: 0.000000
+2023-10-25 13:07:09,575 epoch 4 - iter 1620/1809 - loss 0.04432814 - time (sec): 142.32 - samples/sec: 2380.91 - lr: 0.000034 - momentum: 0.000000
+2023-10-25 13:07:25,700 epoch 4 - iter 1800/1809 - loss 0.04524228 - time (sec): 158.44 - samples/sec: 2383.85 - lr: 0.000033 - momentum: 0.000000
+2023-10-25 13:07:26,573 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:07:26,573 EPOCH 4 done: loss 0.0451 - lr: 0.000033
+2023-10-25 13:07:31,848 DEV : loss 0.20192305743694305 - f1-score (micro avg)  0.6289
+2023-10-25 13:07:31,871 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:07:47,452 epoch 5 - iter 180/1809 - loss 0.02734931 - time (sec): 15.58 - samples/sec: 2412.22 - lr: 0.000033 - momentum: 0.000000
+2023-10-25 13:08:03,819 epoch 5 - iter 360/1809 - loss 0.02324021 - time (sec): 31.95 - samples/sec: 2392.25 - lr: 0.000032 - momentum: 0.000000
+2023-10-25 13:08:19,580 epoch 5 - iter 540/1809 - loss 0.02650141 - time (sec): 47.71 - samples/sec: 2403.80 - lr: 0.000032 - momentum: 0.000000
+2023-10-25 13:08:35,226 epoch 5 - iter 720/1809 - loss 0.02704811 - time (sec): 63.35 - samples/sec: 2417.63 - lr: 0.000031 - momentum: 0.000000
+2023-10-25 13:08:51,415 epoch 5 - iter 900/1809 - loss 0.02877765 - time (sec): 79.54 - samples/sec: 2406.90 - lr: 0.000031 - momentum: 0.000000
+2023-10-25 13:09:07,224 epoch 5 - iter 1080/1809 - loss 0.02961531 - time (sec): 95.35 - samples/sec: 2400.83 - lr: 0.000030 - momentum: 0.000000
+2023-10-25 13:09:23,022 epoch 5 - iter 1260/1809 - loss 0.02938927 - time (sec): 111.15 - samples/sec: 2396.43 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 13:09:38,603 epoch 5 - iter 1440/1809 - loss 0.02946213 - time (sec): 126.73 - samples/sec: 2401.26 - lr: 0.000029 - momentum: 0.000000
+2023-10-25 13:09:54,292 epoch 5 - iter 1620/1809 - loss 0.02947805 - time (sec): 142.42 - samples/sec: 2396.84 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 13:10:10,223 epoch 5 - iter 1800/1809 - loss 0.02955292 - time (sec): 158.35 - samples/sec: 2389.40 - lr: 0.000028 - momentum: 0.000000
+2023-10-25 13:10:10,953 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:10:10,953 EPOCH 5 done: loss 0.0295 - lr: 0.000028
+2023-10-25 13:10:15,727 DEV : loss 0.2949555218219757 - f1-score (micro avg)  0.6355
+2023-10-25 13:10:15,750 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:10:31,928 epoch 6 - iter 180/1809 - loss 0.01655256 - time (sec): 16.18 - samples/sec: 2405.34 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 13:10:47,816 epoch 6 - iter 360/1809 - loss 0.01946603 - time (sec): 32.07 - samples/sec: 2373.06 - lr: 0.000027 - momentum: 0.000000
+2023-10-25 13:11:03,540 epoch 6 - iter 540/1809 - loss 0.01771531 - time (sec): 47.79 - samples/sec: 2366.90 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 13:11:19,762 epoch 6 - iter 720/1809 - loss 0.01794652 - time (sec): 64.01 - samples/sec: 2376.16 - lr: 0.000026 - momentum: 0.000000
+2023-10-25 13:11:35,513 epoch 6 - iter 900/1809 - loss 0.01902434 - time (sec): 79.76 - samples/sec: 2373.75 - lr: 0.000025 - momentum: 0.000000
+2023-10-25 13:11:51,427 epoch 6 - iter 1080/1809 - loss 0.01867401 - time (sec): 95.68 - samples/sec: 2377.37 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 13:12:07,127 epoch 6 - iter 1260/1809 - loss 0.01897470 - time (sec): 111.38 - samples/sec: 2382.57 - lr: 0.000024 - momentum: 0.000000
+2023-10-25 13:12:23,192 epoch 6 - iter 1440/1809 - loss 0.01911851 - time (sec): 127.44 - samples/sec: 2384.79 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 13:12:39,025 epoch 6 - iter 1620/1809 - loss 0.01999373 - time (sec): 143.27 - samples/sec: 2382.18 - lr: 0.000023 - momentum: 0.000000
+2023-10-25 13:12:54,521 epoch 6 - iter 1800/1809 - loss 0.01982448 - time (sec): 158.77 - samples/sec: 2381.69 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 13:12:55,269 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:12:55,269 EPOCH 6 done: loss 0.0198 - lr: 0.000022
+2023-10-25 13:13:00,034 DEV : loss 0.347699373960495 - f1-score (micro avg)  0.6493
+2023-10-25 13:13:00,057 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:13:15,623 epoch 7 - iter 180/1809 - loss 0.01012341 - time (sec): 15.57 - samples/sec: 2404.35 - lr: 0.000022 - momentum: 0.000000
+2023-10-25 13:13:31,454 epoch 7 - iter 360/1809 - loss 0.01305697 - time (sec): 31.40 - samples/sec: 2373.59 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 13:13:47,017 epoch 7 - iter 540/1809 - loss 0.01300877 - time (sec): 46.96 - samples/sec: 2377.11 - lr: 0.000021 - momentum: 0.000000
+2023-10-25 13:14:02,889 epoch 7 - iter 720/1809 - loss 0.01389528 - time (sec): 62.83 - samples/sec: 2376.06 - lr: 0.000020 - momentum: 0.000000
+2023-10-25 13:14:18,735 epoch 7 - iter 900/1809 - loss 0.01408907 - time (sec): 78.68 - samples/sec: 2375.30 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 13:14:34,859 epoch 7 - iter 1080/1809 - loss 0.01370295 - time (sec): 94.80 - samples/sec: 2382.48 - lr: 0.000019 - momentum: 0.000000
+2023-10-25 13:14:50,754 epoch 7 - iter 1260/1809 - loss 0.01366540 - time (sec): 110.70 - samples/sec: 2392.99 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 13:15:06,865 epoch 7 - iter 1440/1809 - loss 0.01400641 - time (sec): 126.81 - samples/sec: 2390.49 - lr: 0.000018 - momentum: 0.000000
+2023-10-25 13:15:22,780 epoch 7 - iter 1620/1809 - loss 0.01385209 - time (sec): 142.72 - samples/sec: 2385.21 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 13:15:38,684 epoch 7 - iter 1800/1809 - loss 0.01412168 - time (sec): 158.63 - samples/sec: 2383.30 - lr: 0.000017 - momentum: 0.000000
+2023-10-25 13:15:39,407 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:15:39,408 EPOCH 7 done: loss 0.0141 - lr: 0.000017
+2023-10-25 13:15:44,698 DEV : loss 0.35314860939979553 - f1-score (micro avg)  0.6557
+2023-10-25 13:15:44,721 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:16:00,867 epoch 8 - iter 180/1809 - loss 0.01022784 - time (sec): 16.14 - samples/sec: 2412.56 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 13:16:17,042 epoch 8 - iter 360/1809 - loss 0.01058094 - time (sec): 32.32 - samples/sec: 2352.04 - lr: 0.000016 - momentum: 0.000000
+2023-10-25 13:16:33,062 epoch 8 - iter 540/1809 - loss 0.01011424 - time (sec): 48.34 - samples/sec: 2361.84 - lr: 0.000015 - momentum: 0.000000
+2023-10-25 13:16:49,047 epoch 8 - iter 720/1809 - loss 0.00966851 - time (sec): 64.32 - samples/sec: 2375.94 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 13:17:04,894 epoch 8 - iter 900/1809 - loss 0.00933864 - time (sec): 80.17 - samples/sec: 2376.95 - lr: 0.000014 - momentum: 0.000000
+2023-10-25 13:17:20,529 epoch 8 - iter 1080/1809 - loss 0.00951050 - time (sec): 95.81 - samples/sec: 2364.76 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 13:17:36,142 epoch 8 - iter 1260/1809 - loss 0.00966767 - time (sec): 111.42 - samples/sec: 2370.92 - lr: 0.000013 - momentum: 0.000000
+2023-10-25 13:17:52,143 epoch 8 - iter 1440/1809 - loss 0.00962221 - time (sec): 127.42 - samples/sec: 2379.62 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 13:18:07,519 epoch 8 - iter 1620/1809 - loss 0.00957778 - time (sec): 142.80 - samples/sec: 2379.27 - lr: 0.000012 - momentum: 0.000000
+2023-10-25 13:18:23,395 epoch 8 - iter 1800/1809 - loss 0.00960260 - time (sec): 158.67 - samples/sec: 2382.90 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 13:18:24,169 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:18:24,169 EPOCH 8 done: loss 0.0096 - lr: 0.000011
+2023-10-25 13:18:29,463 DEV : loss 0.4076786935329437 - f1-score (micro avg)  0.6491
+2023-10-25 13:18:29,486 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:18:44,946 epoch 9 - iter 180/1809 - loss 0.00346298 - time (sec): 15.46 - samples/sec: 2391.49 - lr: 0.000011 - momentum: 0.000000
+2023-10-25 13:19:01,070 epoch 9 - iter 360/1809 - loss 0.00386564 - time (sec): 31.58 - samples/sec: 2399.66 - lr: 0.000010 - momentum: 0.000000
+2023-10-25 13:19:16,951 epoch 9 - iter 540/1809 - loss 0.00562997 - time (sec): 47.46 - samples/sec: 2400.68 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 13:19:32,422 epoch 9 - iter 720/1809 - loss 0.00546924 - time (sec): 62.94 - samples/sec: 2394.18 - lr: 0.000009 - momentum: 0.000000
+2023-10-25 13:19:48,301 epoch 9 - iter 900/1809 - loss 0.00581289 - time (sec): 78.81 - samples/sec: 2392.02 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 13:20:04,825 epoch 9 - iter 1080/1809 - loss 0.00611858 - time (sec): 95.34 - samples/sec: 2384.94 - lr: 0.000008 - momentum: 0.000000
+2023-10-25 13:20:21,183 epoch 9 - iter 1260/1809 - loss 0.00643895 - time (sec): 111.70 - samples/sec: 2378.78 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 13:20:37,254 epoch 9 - iter 1440/1809 - loss 0.00648270 - time (sec): 127.77 - samples/sec: 2383.17 - lr: 0.000007 - momentum: 0.000000
+2023-10-25 13:20:52,352 epoch 9 - iter 1620/1809 - loss 0.00637081 - time (sec): 142.86 - samples/sec: 2377.49 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 13:21:08,288 epoch 9 - iter 1800/1809 - loss 0.00619420 - time (sec): 158.80 - samples/sec: 2382.08 - lr: 0.000006 - momentum: 0.000000
+2023-10-25 13:21:09,058 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:21:09,058 EPOCH 9 done: loss 0.0062 - lr: 0.000006
+2023-10-25 13:21:14,367 DEV : loss 0.4059355556964874 - f1-score (micro avg)  0.6474
+2023-10-25 13:21:14,390 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:21:30,210 epoch 10 - iter 180/1809 - loss 0.00238887 - time (sec): 15.82 - samples/sec: 2406.56 - lr: 0.000005 - momentum: 0.000000
+2023-10-25 13:21:45,960 epoch 10 - iter 360/1809 - loss 0.00251156 - time (sec): 31.57 - samples/sec: 2405.41 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 13:22:01,793 epoch 10 - iter 540/1809 - loss 0.00290608 - time (sec): 47.40 - samples/sec: 2395.50 - lr: 0.000004 - momentum: 0.000000
+2023-10-25 13:22:17,530 epoch 10 - iter 720/1809 - loss 0.00315655 - time (sec): 63.14 - samples/sec: 2387.64 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 13:22:33,117 epoch 10 - iter 900/1809 - loss 0.00334403 - time (sec): 78.73 - samples/sec: 2379.43 - lr: 0.000003 - momentum: 0.000000
+2023-10-25 13:22:48,770 epoch 10 - iter 1080/1809 - loss 0.00312517 - time (sec): 94.38 - samples/sec: 2380.87 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 13:23:04,901 epoch 10 - iter 1260/1809 - loss 0.00323274 - time (sec): 110.51 - samples/sec: 2383.07 - lr: 0.000002 - momentum: 0.000000
+2023-10-25 13:23:21,257 epoch 10 - iter 1440/1809 - loss 0.00317762 - time (sec): 126.87 - samples/sec: 2385.06 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 13:23:37,428 epoch 10 - iter 1620/1809 - loss 0.00332409 - time (sec): 143.04 - samples/sec: 2383.07 - lr: 0.000001 - momentum: 0.000000
+2023-10-25 13:23:52,987 epoch 10 - iter 1800/1809 - loss 0.00349659 - time (sec): 158.60 - samples/sec: 2384.70 - lr: 0.000000 - momentum: 0.000000
+2023-10-25 13:23:53,696 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:23:53,697 EPOCH 10 done: loss 0.0035 - lr: 0.000000
+2023-10-25 13:23:59,011 DEV : loss 0.4234822392463684 - f1-score (micro avg)  0.6419
+2023-10-25 13:23:59,603 ----------------------------------------------------------------------------------------------------
+2023-10-25 13:23:59,604 Loading model from best epoch ...
+2023-10-25 13:24:01,370 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 13:24:07,107 
+Results:
+- F-score (micro) 0.6591
+- F-score (macro) 0.4663
+- Accuracy 0.5014
+
+By class:
+              precision    recall  f1-score   support
+
+         loc     0.6863    0.7479    0.7158       591
+        pers     0.5734    0.7115    0.6350       357
+         org     0.5000    0.0253    0.0482        79
+
+   micro avg     0.6398    0.6796    0.6591      1027
+   macro avg     0.5866    0.4949    0.4663      1027
+weighted avg     0.6327    0.6796    0.6364      1027
+
+2023-10-25 13:24:07,107 ----------------------------------------------------------------------------------------------------