Added model without flair embeddings

loss.tsv

@@ -1,3 +1,3 @@
 EPOCH	TIMESTAMP	BAD_EPOCHS	LEARNING_RATE	TRAIN_LOSS	DEV_LOSS	DEV_PRECISION	DEV_RECALL	DEV_F1	DEV_ACCURACY
-1	00:43:17	0	0.0100	0.189008099097259	0.06317088007926941	0.9458	0.9717	0.9585	0.9206
-2	01:01:40	0	0.0100	0.09155321446036903	0.04371843859553337	0.9713	0.9785	0.9749	0.9511
+1	14:24:53	0	0.0100	0.291245240352544	0.06397613137960434	0.9724	0.9736	0.973	0.9477
+2	14:42:51	0	0.0100	0.13731835639464673	0.05747831612825394	0.9826	0.9863	0.9844	0.9696

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba47fe584e142b59f730a6261f9803f7ece0667ea1a48948c84803fb33ffeb9
-size 754011805
+oid sha256:1c623f10dba949ae162389713d32ce968220b060cfad3fdb180300495a7f35cc
+size 714487533

training.log

@@ -1,408 +1,390 @@
-2022-10-01 00:23:25,105 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:23:25,107 Model: "SequenceTagger(
-  (embeddings): StackedEmbeddings(
-    (list_embedding_0): TransformerWordEmbeddings(
-      (model): BertModel(
-        (embeddings): BertEmbeddings(
-          (word_embeddings): Embedding(119547, 768, padding_idx=0)
-          (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()
+2022-10-04 14:07:15,489 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:07:15,492 Model: "SequenceTagger(
+  (embeddings): TransformerWordEmbeddings(
+    (model): BertModel(
+      (embeddings): BertEmbeddings(
+        (word_embeddings): Embedding(119547, 768, padding_idx=0)
+        (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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)
               )
             )
-            (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()
+            (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): BertOutput(
-                (dense): Linear(in_features=3072, out_features=768, bias=True)
+              (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()
-        )
-      )
-    )
-    (list_embedding_1): FlairEmbeddings(
-      (lm): LanguageModel(
-        (drop): Dropout(p=0.5, inplace=False)
-        (encoder): Embedding(275, 100)
-        (rnn): LSTM(100, 1024)
-        (decoder): Linear(in_features=1024, out_features=275, bias=True)
       )
-    )
-    (list_embedding_2): FlairEmbeddings(
-      (lm): LanguageModel(
-        (drop): Dropout(p=0.5, inplace=False)
-        (encoder): Embedding(275, 100)
-        (rnn): LSTM(100, 1024)
-        (decoder): Linear(in_features=1024, out_features=275, bias=True)
+      (pooler): BertPooler(
+        (dense): Linear(in_features=768, out_features=768, bias=True)
+        (activation): Tanh()
       )
     )
   )
+  (dropout): Dropout(p=0.3, inplace=False)
   (word_dropout): WordDropout(p=0.05)
   (locked_dropout): LockedDropout(p=0.5)
-  (embedding2nn): Linear(in_features=2816, out_features=2816, bias=True)
-  (linear): Linear(in_features=2816, out_features=13, bias=True)
+  (linear): Linear(in_features=768, out_features=13, bias=True)
   (loss_function): CrossEntropyLoss()
 )"
-2022-10-01 00:23:25,114 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:23:25,115 Corpus: "Corpus: 70000 train + 15000 dev + 15000 test sentences"
-2022-10-01 00:23:25,115 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:23:25,115 Parameters:
-2022-10-01 00:23:25,116  - learning_rate: "0.010000"
-2022-10-01 00:23:25,116  - mini_batch_size: "8"
-2022-10-01 00:23:25,116  - patience: "3"
-2022-10-01 00:23:25,116  - anneal_factor: "0.5"
-2022-10-01 00:23:25,116  - max_epochs: "2"
-2022-10-01 00:23:25,116  - shuffle: "True"
-2022-10-01 00:23:25,117  - train_with_dev: "False"
-2022-10-01 00:23:25,117  - batch_growth_annealing: "False"
-2022-10-01 00:23:25,117 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:23:25,117 Model training base path: "c:\Users\Ivan\Documents\Projects\Yoda\NER\model\flair\src\..\models\mix_trans_word"
-2022-10-01 00:23:25,117 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:23:25,118 Device: cuda:0
-2022-10-01 00:23:25,118 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:23:25,118 Embeddings storage mode: cpu
-2022-10-01 00:23:25,119 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:25:10,652 epoch 1 - iter 875/8750 - loss 0.52734710 - samples/sec: 66.36 - lr: 0.010000
-2022-10-01 00:26:56,050 epoch 1 - iter 1750/8750 - loss 0.40571165 - samples/sec: 66.45 - lr: 0.010000
-2022-10-01 00:28:42,758 epoch 1 - iter 2625/8750 - loss 0.33981350 - samples/sec: 65.63 - lr: 0.010000
-2022-10-01 00:30:27,826 epoch 1 - iter 3500/8750 - loss 0.29553411 - samples/sec: 66.66 - lr: 0.010000
-2022-10-01 00:32:13,605 epoch 1 - iter 4375/8750 - loss 0.26472648 - samples/sec: 66.21 - lr: 0.010000
-2022-10-01 00:33:58,962 epoch 1 - iter 5250/8750 - loss 0.24119392 - samples/sec: 66.47 - lr: 0.010000
-2022-10-01 00:35:44,264 epoch 1 - iter 6125/8750 - loss 0.22350560 - samples/sec: 66.50 - lr: 0.010000
-2022-10-01 00:37:29,676 epoch 1 - iter 7000/8750 - loss 0.20938707 - samples/sec: 66.43 - lr: 0.010000
-2022-10-01 00:39:17,828 epoch 1 - iter 7875/8750 - loss 0.19801233 - samples/sec: 64.75 - lr: 0.010000
-2022-10-01 00:41:05,621 epoch 1 - iter 8750/8750 - loss 0.18900810 - samples/sec: 64.98 - lr: 0.010000
-2022-10-01 00:41:05,624 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:41:05,624 EPOCH 1 done: loss 0.1890 - lr 0.010000
-2022-10-01 00:43:16,083 Evaluating as a multi-label problem: False
-2022-10-01 00:43:16,227 DEV : loss 0.06317088007926941 - f1-score (micro avg)  0.9585
-2022-10-01 00:43:17,308 BAD EPOCHS (no improvement): 0
-2022-10-01 00:43:17,309 saving best model
-2022-10-01 00:43:18,885 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:45:00,373 epoch 2 - iter 875/8750 - loss 0.09938527 - samples/sec: 69.02 - lr: 0.010000
-2022-10-01 00:46:39,918 epoch 2 - iter 1750/8750 - loss 0.09782604 - samples/sec: 70.36 - lr: 0.010000
-2022-10-01 00:48:19,288 epoch 2 - iter 2625/8750 - loss 0.09732946 - samples/sec: 70.50 - lr: 0.010000
-2022-10-01 00:49:56,913 epoch 2 - iter 3500/8750 - loss 0.09652202 - samples/sec: 71.76 - lr: 0.010000
-2022-10-01 00:51:35,781 epoch 2 - iter 4375/8750 - loss 0.09592801 - samples/sec: 70.86 - lr: 0.010000
-2022-10-01 00:53:12,838 epoch 2 - iter 5250/8750 - loss 0.09478132 - samples/sec: 72.17 - lr: 0.010000
-2022-10-01 00:54:49,247 epoch 2 - iter 6125/8750 - loss 0.09405506 - samples/sec: 72.65 - lr: 0.010000
-2022-10-01 00:56:26,656 epoch 2 - iter 7000/8750 - loss 0.09270363 - samples/sec: 71.90 - lr: 0.010000
-2022-10-01 00:58:04,050 epoch 2 - iter 7875/8750 - loss 0.09222568 - samples/sec: 71.92 - lr: 0.010000
-2022-10-01 00:59:41,351 epoch 2 - iter 8750/8750 - loss 0.09155321 - samples/sec: 71.98 - lr: 0.010000
-2022-10-01 00:59:41,359 ----------------------------------------------------------------------------------------------------
-2022-10-01 00:59:41,360 EPOCH 2 done: loss 0.0916 - lr 0.010000
-2022-10-01 01:01:38,941 Evaluating as a multi-label problem: False
-2022-10-01 01:01:39,054 DEV : loss 0.04371843859553337 - f1-score (micro avg)  0.9749
-2022-10-01 01:01:40,056 BAD EPOCHS (no improvement): 0
-2022-10-01 01:01:40,058 saving best model
-2022-10-01 01:01:42,979 ----------------------------------------------------------------------------------------------------
-2022-10-01 01:01:42,986 loading file c:\Users\Ivan\Documents\Projects\Yoda\NER\model\flair\src\..\models\mix_trans_word\best-model.pt
-2022-10-01 01:01:46,879 SequenceTagger predicts: Dictionary with 13 tags: O, S-brand, B-brand, E-brand, I-brand, S-size, B-size, E-size, I-size, S-color, B-color, E-color, I-color
-2022-10-01 01:03:40,258 Evaluating as a multi-label problem: False
-2022-10-01 01:03:40,388 0.9719	0.9777	0.9748	0.951
-2022-10-01 01:03:40,389 
+2022-10-04 14:07:15,510 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:07:15,510 Corpus: "Corpus: 70000 train + 15000 dev + 15000 test sentences"
+2022-10-04 14:07:15,510 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:07:15,511 Parameters:
+2022-10-04 14:07:15,511  - learning_rate: "0.010000"
+2022-10-04 14:07:15,511  - mini_batch_size: "8"
+2022-10-04 14:07:15,511  - patience: "3"
+2022-10-04 14:07:15,512  - anneal_factor: "0.5"
+2022-10-04 14:07:15,512  - max_epochs: "2"
+2022-10-04 14:07:15,512  - shuffle: "True"
+2022-10-04 14:07:15,512  - train_with_dev: "False"
+2022-10-04 14:07:15,513  - batch_growth_annealing: "False"
+2022-10-04 14:07:15,513 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:07:15,513 Model training base path: "c:\Users\Ivan\Documents\Projects\Yoda\NER\model\flair\src\..\models\trans_sm_flair"
+2022-10-04 14:07:15,513 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:07:15,513 Device: cuda:0
+2022-10-04 14:07:15,514 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:07:15,514 Embeddings storage mode: cpu
+2022-10-04 14:07:15,514 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:08:50,056 epoch 1 - iter 875/8750 - loss 0.77736243 - samples/sec: 74.10 - lr: 0.010000
+2022-10-04 14:10:25,613 epoch 1 - iter 1750/8750 - loss 0.58654474 - samples/sec: 73.31 - lr: 0.010000
+2022-10-04 14:12:00,221 epoch 1 - iter 2625/8750 - loss 0.49473747 - samples/sec: 74.05 - lr: 0.010000
+2022-10-04 14:13:35,035 epoch 1 - iter 3500/8750 - loss 0.43711232 - samples/sec: 73.87 - lr: 0.010000
+2022-10-04 14:15:08,344 epoch 1 - iter 4375/8750 - loss 0.39713865 - samples/sec: 75.06 - lr: 0.010000
+2022-10-04 14:16:41,989 epoch 1 - iter 5250/8750 - loss 0.36731971 - samples/sec: 74.80 - lr: 0.010000
+2022-10-04 14:18:17,847 epoch 1 - iter 6125/8750 - loss 0.34209381 - samples/sec: 73.07 - lr: 0.010000
+2022-10-04 14:19:52,115 epoch 1 - iter 7000/8750 - loss 0.32256861 - samples/sec: 74.30 - lr: 0.010000
+2022-10-04 14:21:26,066 epoch 1 - iter 7875/8750 - loss 0.30596431 - samples/sec: 74.55 - lr: 0.010000
+2022-10-04 14:23:00,059 epoch 1 - iter 8750/8750 - loss 0.29124524 - samples/sec: 74.51 - lr: 0.010000
+2022-10-04 14:23:00,061 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:23:00,062 EPOCH 1 done: loss 0.2912 - lr 0.010000
+2022-10-04 14:24:52,210 Evaluating as a multi-label problem: False
+2022-10-04 14:24:52,424 DEV : loss 0.06397613137960434 - f1-score (micro avg)  0.973
+2022-10-04 14:24:53,223 BAD EPOCHS (no improvement): 0
+2022-10-04 14:24:54,431 saving best model
+2022-10-04 14:24:55,749 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:26:31,875 epoch 2 - iter 875/8750 - loss 0.15239591 - samples/sec: 72.88 - lr: 0.010000
+2022-10-04 14:28:12,311 epoch 2 - iter 1750/8750 - loss 0.15109719 - samples/sec: 69.74 - lr: 0.010000
+2022-10-04 14:29:49,414 epoch 2 - iter 2625/8750 - loss 0.15017726 - samples/sec: 72.14 - lr: 0.010000
+2022-10-04 14:31:22,789 epoch 2 - iter 3500/8750 - loss 0.14709937 - samples/sec: 75.01 - lr: 0.010000
+2022-10-04 14:32:56,365 epoch 2 - iter 4375/8750 - loss 0.14490590 - samples/sec: 74.87 - lr: 0.010000
+2022-10-04 14:34:29,769 epoch 2 - iter 5250/8750 - loss 0.14379219 - samples/sec: 75.00 - lr: 0.010000
+2022-10-04 14:36:04,122 epoch 2 - iter 6125/8750 - loss 0.14272196 - samples/sec: 74.24 - lr: 0.010000
+2022-10-04 14:37:40,084 epoch 2 - iter 7000/8750 - loss 0.14024151 - samples/sec: 73.00 - lr: 0.010000
+2022-10-04 14:39:15,077 epoch 2 - iter 7875/8750 - loss 0.13892120 - samples/sec: 73.73 - lr: 0.010000
+2022-10-04 14:40:48,611 epoch 2 - iter 8750/8750 - loss 0.13731836 - samples/sec: 74.89 - lr: 0.010000
+2022-10-04 14:40:48,617 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:40:48,617 EPOCH 2 done: loss 0.1373 - lr 0.010000
+2022-10-04 14:42:50,048 Evaluating as a multi-label problem: False
+2022-10-04 14:42:50,277 DEV : loss 0.05747831612825394 - f1-score (micro avg)  0.9844
+2022-10-04 14:42:51,053 BAD EPOCHS (no improvement): 0
+2022-10-04 14:42:52,333 saving best model
+2022-10-04 14:42:54,576 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:42:54,600 loading file c:\Users\Ivan\Documents\Projects\Yoda\NER\model\flair\src\..\models\trans_sm_flair\best-model.pt
+2022-10-04 14:42:57,086 SequenceTagger predicts: Dictionary with 13 tags: O, S-size, B-size, E-size, I-size, S-brand, B-brand, E-brand, I-brand, S-color, B-color, E-color, I-color
+2022-10-04 14:44:29,459 Evaluating as a multi-label problem: False
+2022-10-04 14:44:29,668 0.9816	0.9857	0.9837	0.9679
+2022-10-04 14:44:29,669 
 Results:
-- F-score (micro) 0.9748
-- F-score (macro) 0.9624
-- Accuracy 0.951
+- F-score (micro) 0.9837
+- F-score (macro) 0.9843
+- Accuracy 0.9679
 
 By class:
               precision    recall  f1-score   support
 
-       brand     0.9779    0.9849    0.9814     11779
-        size     0.9780    0.9821    0.9800      3125
-       color     0.9249    0.9264    0.9256      1915
+        size     0.9820    0.9859    0.9839     17988
+       brand     0.9773    0.9860    0.9817     11674
+       color     0.9905    0.9840    0.9872      5070
 
-   micro avg     0.9719    0.9777    0.9748     16819
-   macro avg     0.9603    0.9644    0.9624     16819
-weighted avg     0.9719    0.9777    0.9748     16819
+   micro avg     0.9816    0.9857    0.9837     34732
+   macro avg     0.9833    0.9853    0.9843     34732
+weighted avg     0.9816    0.9857    0.9837     34732
 
-2022-10-01 01:03:40,391 ----------------------------------------------------------------------------------------------------
+2022-10-04 14:44:29,670 ----------------------------------------------------------------------------------------------------