Training done

added_tokens.json

@@ -12,7 +12,6 @@
   "<s_birth_date>": 57531,
   "<s_cnh>": 57541,
   "<s_cpf>": 57533,
-  "<s_docparse>": 57545,
   "<s_expedition_date>": 57539,
   "<s_filiacao>": 57535,
   "<s_iitcdip>": 57523,

special_tokens_map.json

@@ -141,14 +141,14 @@
       "single_word": false
     },
     {
-      "content": "<s_docparse>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<s_docparse>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer.json

@@ -254,15 +254,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 57545,
-      "content": "<s_docparse>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -223,14 +223,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "57545": {
-      "content": "<s_docparse>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
@@ -254,8 +246,8 @@
     "</s_cnh>",
     "<s_naturality>",
     "</s_naturality>",
-    "<s_docparse>",
-    "<s_docparse>"
+    "<s>",
+    "<s>"
   ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,