Training done

added_tokens.json

@@ -1,30 +1,23 @@
 {
-  "</s_IDESP>": 57542,
-  "</s_birthDate>": 57538,
-  "</s_birth_date>": 57545,
-  "</s_expirationDate>": 57540,
-  "</s_expiration_date>": 57547,
+  "</s_birth_date>": 57538,
+  "</s_expiration_date>": 57540,
   "</s_idNumber>": 57536,
   "</s_name>": 57526,
   "</s_nationality>": 57534,
   "</s_second_surname>": 57530,
   "</s_sex>": 57532,
-  "</s_support_number>": 57549,
+  "</s_support_number>": 57542,
   "</s_surname>": 57528,
-  "<s_IDESP>": 57541,
-  "<s_birthDate>": 57537,
-  "<s_birth_date>": 57544,
-  "<s_dnis>": 57543,
-  "<s_dnis_2024>": 57550,
-  "<s_expirationDate>": 57539,
-  "<s_expiration_date>": 57546,
+  "<s_birth_date>": 57537,
+  "<s_dnis_2024>": 57543,
+  "<s_expiration_date>": 57539,
   "<s_idNumber>": 57535,
   "<s_iitcdip>": 57523,
   "<s_name>": 57525,
   "<s_nationality>": 57533,
   "<s_second_surname>": 57529,
   "<s_sex>": 57531,
-  "<s_support_number>": 57548,
+  "<s_support_number>": 57541,
   "<s_surname>": 57527,
   "<s_synthdog>": 57524,
   "<sep/>": 57522

tokenizer_config.json

@@ -161,62 +161,6 @@
       "special": false
     },
     "57537": {
-      "content": "<s_birthDate>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57538": {
-      "content": "</s_birthDate>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57539": {
-      "content": "<s_expirationDate>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57540": {
-      "content": "</s_expirationDate>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57541": {
-      "content": "<s_IDESP>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57542": {
-      "content": "</s_IDESP>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57543": {
-      "content": "<s_dnis>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57544": {
       "content": "<s_birth_date>",
       "lstrip": false,
       "normalized": true,
@@ -224,7 +168,7 @@
       "single_word": false,
       "special": false
     },
-    "57545": {
+    "57538": {
       "content": "</s_birth_date>",
       "lstrip": false,
       "normalized": true,
@@ -232,7 +176,7 @@
       "single_word": false,
       "special": false
     },
-    "57546": {
+    "57539": {
       "content": "<s_expiration_date>",
       "lstrip": false,
       "normalized": true,
@@ -240,7 +184,7 @@
       "single_word": false,
       "special": false
     },
-    "57547": {
+    "57540": {
       "content": "</s_expiration_date>",
       "lstrip": false,
       "normalized": true,
@@ -248,7 +192,7 @@
       "single_word": false,
       "special": false
     },
-    "57548": {
+    "57541": {
       "content": "<s_support_number>",
       "lstrip": false,
       "normalized": true,
@@ -256,7 +200,7 @@
       "single_word": false,
       "special": false
     },
-    "57549": {
+    "57542": {
       "content": "</s_support_number>",
       "lstrip": false,
       "normalized": true,
@@ -264,7 +208,7 @@
       "single_word": false,
       "special": false
     },
-    "57550": {
+    "57543": {
       "content": "<s_dnis_2024>",
       "lstrip": false,
       "normalized": true,
@@ -282,18 +226,11 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "max_length": 768,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "processor_class": "DonutProcessor",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }