Training started

added_tokens.json

@@ -1,72 +1,60 @@
 {
-  "</s_AMOUNT_DUE>": 57568,
-  "</s_BILL_TO>": 57586,
+  "</s_BILL_TO>": 57574,
   "</s_BUYER>": 57526,
   "</s_CONDITIONS>": 57528,
   "</s_DATE>": 57530,
   "</s_DISCOUNT>": 57532,
   "</s_DUE_DATE>": 57534,
-  "</s_GST(1%)>": 57576,
-  "</s_GST(12%)>": 57582,
-  "</s_GST(18%)>": 57580,
-  "</s_GST(20%)>": 57578,
-  "</s_GST(5%)>": 57584,
-  "</s_GST(7%)>": 57588,
-  "</s_GST(9%)>": 57590,
+  "</s_GST(7%)>": 57572,
+  "</s_GST(9%)>": 57576,
   "</s_GSTIN>": 57570,
-  "</s_GSTIN_BUYER>": 57562,
-  "</s_GSTIN_SELLER>": 57564,
+  "</s_GSTIN_BUYER>": 57552,
+  "</s_GSTIN_SELLER>": 57568,
   "</s_LOGO>": 57548,
   "</s_NOTE>": 57538,
   "</s_NUMBER>": 57536,
-  "</s_PAYMENT_DETAILS>": 57558,
-  "</s_PO_NUMBER>": 57572,
+  "</s_PAYMENT_DETAILS>": 57554,
+  "</s_PO_NUMBER>": 57556,
   "</s_SELLER_ADDRESS>": 57540,
   "</s_SELLER_EMAIL>": 57542,
   "</s_SELLER_NAME>": 57544,
-  "</s_SELLER_SITE>": 57574,
-  "</s_SEND_TO>": 57566,
-  "</s_SUB_TOTAL>": 57552,
+  "</s_SELLER_SITE>": 57558,
+  "</s_SEND_TO>": 57578,
+  "</s_SUB_TOTAL>": 57560,
   "</s_TABLE>": 57550,
-  "</s_TAX>": 57554,
-  "</s_TITLE>": 57556,
+  "</s_TAX>": 57562,
+  "</s_TITLE>": 57564,
   "</s_TOTAL>": 57546,
-  "</s_TOTAL_WORDS>": 57560,
-  "<s_AMOUNT_DUE>": 57567,
-  "<s_BILL_TO>": 57585,
+  "</s_TOTAL_WORDS>": 57566,
+  "<s_BILL_TO>": 57573,
   "<s_BUYER>": 57525,
   "<s_CONDITIONS>": 57527,
   "<s_DATE>": 57529,
   "<s_DISCOUNT>": 57531,
   "<s_DUE_DATE>": 57533,
-  "<s_GST(1%)>": 57575,
-  "<s_GST(12%)>": 57581,
-  "<s_GST(18%)>": 57579,
-  "<s_GST(20%)>": 57577,
-  "<s_GST(5%)>": 57583,
-  "<s_GST(7%)>": 57587,
-  "<s_GST(9%)>": 57589,
+  "<s_GST(7%)>": 57571,
+  "<s_GST(9%)>": 57575,
   "<s_GSTIN>": 57569,
-  "<s_GSTIN_BUYER>": 57561,
-  "<s_GSTIN_SELLER>": 57563,
+  "<s_GSTIN_BUYER>": 57551,
+  "<s_GSTIN_SELLER>": 57567,
   "<s_LOGO>": 57547,
   "<s_NOTE>": 57537,
   "<s_NUMBER>": 57535,
-  "<s_PAYMENT_DETAILS>": 57557,
-  "<s_PO_NUMBER>": 57571,
+  "<s_PAYMENT_DETAILS>": 57553,
+  "<s_PO_NUMBER>": 57555,
   "<s_SELLER_ADDRESS>": 57539,
   "<s_SELLER_EMAIL>": 57541,
   "<s_SELLER_NAME>": 57543,
-  "<s_SELLER_SITE>": 57573,
-  "<s_SEND_TO>": 57565,
-  "<s_SUB_TOTAL>": 57551,
+  "<s_SELLER_SITE>": 57557,
+  "<s_SEND_TO>": 57577,
+  "<s_SUB_TOTAL>": 57559,
   "<s_TABLE>": 57549,
-  "<s_TAX>": 57553,
-  "<s_TITLE>": 57555,
+  "<s_TAX>": 57561,
+  "<s_TITLE>": 57563,
   "<s_TOTAL>": 57545,
-  "<s_TOTAL_WORDS>": 57559,
+  "<s_TOTAL_WORDS>": 57565,
   "<s_iitcdip>": 57523,
-  "<s_invoice>": 57591,
+  "<s_invoice>": 57579,
   "<s_synthdog>": 57524,
   "<sep/>": 57522
 }

tokenizer.json

@@ -325,7 +325,7 @@
     },
     {
       "id": 57551,
-      "content": "<s_SUB_TOTAL>",
+      "content": "<s_GSTIN_BUYER>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -334,7 +334,7 @@
     },
     {
       "id": 57552,
-      "content": "</s_SUB_TOTAL>",
+      "content": "</s_GSTIN_BUYER>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -343,7 +343,7 @@
     },
     {
       "id": 57553,
-      "content": "<s_TAX>",
+      "content": "<s_PAYMENT_DETAILS>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -352,7 +352,7 @@
     },
     {
       "id": 57554,
-      "content": "</s_TAX>",
+      "content": "</s_PAYMENT_DETAILS>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -361,7 +361,7 @@
     },
     {
       "id": 57555,
-      "content": "<s_TITLE>",
+      "content": "<s_PO_NUMBER>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -370,7 +370,7 @@
     },
     {
       "id": 57556,
-      "content": "</s_TITLE>",
+      "content": "</s_PO_NUMBER>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -379,7 +379,7 @@
     },
     {
       "id": 57557,
-      "content": "<s_PAYMENT_DETAILS>",
+      "content": "<s_SELLER_SITE>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -388,7 +388,7 @@
     },
     {
       "id": 57558,
-      "content": "</s_PAYMENT_DETAILS>",
+      "content": "</s_SELLER_SITE>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -397,7 +397,7 @@
     },
     {
       "id": 57559,
-      "content": "<s_TOTAL_WORDS>",
+      "content": "<s_SUB_TOTAL>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -406,7 +406,7 @@
     },
     {
       "id": 57560,
-      "content": "</s_TOTAL_WORDS>",
+      "content": "</s_SUB_TOTAL>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -415,7 +415,7 @@
     },
     {
       "id": 57561,
-      "content": "<s_GSTIN_BUYER>",
+      "content": "<s_TAX>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -424,7 +424,7 @@
     },
     {
       "id": 57562,
-      "content": "</s_GSTIN_BUYER>",
+      "content": "</s_TAX>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -433,7 +433,7 @@
     },
     {
       "id": 57563,
-      "content": "<s_GSTIN_SELLER>",
+      "content": "<s_TITLE>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -442,7 +442,7 @@
     },
     {
       "id": 57564,
-      "content": "</s_GSTIN_SELLER>",
+      "content": "</s_TITLE>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -451,7 +451,7 @@
     },
     {
       "id": 57565,
-      "content": "<s_SEND_TO>",
+      "content": "<s_TOTAL_WORDS>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -460,7 +460,7 @@
     },
     {
       "id": 57566,
-      "content": "</s_SEND_TO>",
+      "content": "</s_TOTAL_WORDS>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -469,7 +469,7 @@
     },
     {
       "id": 57567,
-      "content": "<s_AMOUNT_DUE>",
+      "content": "<s_GSTIN_SELLER>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -478,7 +478,7 @@
     },
     {
       "id": 57568,
-      "content": "</s_AMOUNT_DUE>",
+      "content": "</s_GSTIN_SELLER>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -505,7 +505,7 @@
     },
     {
       "id": 57571,
-      "content": "<s_PO_NUMBER>",
+      "content": "<s_GST(7%)>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -514,7 +514,7 @@
     },
     {
       "id": 57572,
-      "content": "</s_PO_NUMBER>",
+      "content": "</s_GST(7%)>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -523,7 +523,7 @@
     },
     {
       "id": 57573,
-      "content": "<s_SELLER_SITE>",
+      "content": "<s_BILL_TO>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -532,7 +532,7 @@
     },
     {
       "id": 57574,
-      "content": "</s_SELLER_SITE>",
+      "content": "</s_BILL_TO>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -541,7 +541,7 @@
     },
     {
       "id": 57575,
-      "content": "<s_GST(1%)>",
+      "content": "<s_GST(9%)>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -550,7 +550,7 @@
     },
     {
       "id": 57576,
-      "content": "</s_GST(1%)>",
+      "content": "</s_GST(9%)>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -559,7 +559,7 @@
     },
     {
       "id": 57577,
-      "content": "<s_GST(20%)>",
+      "content": "<s_SEND_TO>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -568,7 +568,7 @@
     },
     {
       "id": 57578,
-      "content": "</s_GST(20%)>",
+      "content": "</s_SEND_TO>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -577,114 +577,6 @@
     },
     {
       "id": 57579,
-      "content": "<s_GST(18%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57580,
-      "content": "</s_GST(18%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57581,
-      "content": "<s_GST(12%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57582,
-      "content": "</s_GST(12%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57583,
-      "content": "<s_GST(5%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57584,
-      "content": "</s_GST(5%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57585,
-      "content": "<s_BILL_TO>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57586,
-      "content": "</s_BILL_TO>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57587,
-      "content": "<s_GST(7%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57588,
-      "content": "</s_GST(7%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57589,
-      "content": "<s_GST(9%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57590,
-      "content": "</s_GST(9%)>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
-    },
-    {
-      "id": 57591,
       "content": "<s_invoice>",
       "single_word": false,
       "lstrip": false,

tokenizer_config.json

@@ -273,7 +273,7 @@
       "special": false
     },
     "57551": {
-      "content": "<s_SUB_TOTAL>",
+      "content": "<s_GSTIN_BUYER>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -281,7 +281,7 @@
       "special": false
     },
     "57552": {
-      "content": "</s_SUB_TOTAL>",
+      "content": "</s_GSTIN_BUYER>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -289,7 +289,7 @@
       "special": false
     },
     "57553": {
-      "content": "<s_TAX>",
+      "content": "<s_PAYMENT_DETAILS>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -297,7 +297,7 @@
       "special": false
     },
     "57554": {
-      "content": "</s_TAX>",
+      "content": "</s_PAYMENT_DETAILS>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -305,7 +305,7 @@
       "special": false
     },
     "57555": {
-      "content": "<s_TITLE>",
+      "content": "<s_PO_NUMBER>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -313,7 +313,7 @@
       "special": false
     },
     "57556": {
-      "content": "</s_TITLE>",
+      "content": "</s_PO_NUMBER>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -321,7 +321,7 @@
       "special": false
     },
     "57557": {
-      "content": "<s_PAYMENT_DETAILS>",
+      "content": "<s_SELLER_SITE>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -329,7 +329,7 @@
       "special": false
     },
     "57558": {
-      "content": "</s_PAYMENT_DETAILS>",
+      "content": "</s_SELLER_SITE>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -337,7 +337,7 @@
       "special": false
     },
     "57559": {
-      "content": "<s_TOTAL_WORDS>",
+      "content": "<s_SUB_TOTAL>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -345,7 +345,7 @@
       "special": false
     },
     "57560": {
-      "content": "</s_TOTAL_WORDS>",
+      "content": "</s_SUB_TOTAL>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -353,7 +353,7 @@
       "special": false
     },
     "57561": {
-      "content": "<s_GSTIN_BUYER>",
+      "content": "<s_TAX>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -361,7 +361,7 @@
       "special": false
     },
     "57562": {
-      "content": "</s_GSTIN_BUYER>",
+      "content": "</s_TAX>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -369,7 +369,7 @@
       "special": false
     },
     "57563": {
-      "content": "<s_GSTIN_SELLER>",
+      "content": "<s_TITLE>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -377,7 +377,7 @@
       "special": false
     },
     "57564": {
-      "content": "</s_GSTIN_SELLER>",
+      "content": "</s_TITLE>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -385,7 +385,7 @@
       "special": false
     },
     "57565": {
-      "content": "<s_SEND_TO>",
+      "content": "<s_TOTAL_WORDS>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -393,7 +393,7 @@
       "special": false
     },
     "57566": {
-      "content": "</s_SEND_TO>",
+      "content": "</s_TOTAL_WORDS>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -401,7 +401,7 @@
       "special": false
     },
     "57567": {
-      "content": "<s_AMOUNT_DUE>",
+      "content": "<s_GSTIN_SELLER>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -409,7 +409,7 @@
       "special": false
     },
     "57568": {
-      "content": "</s_AMOUNT_DUE>",
+      "content": "</s_GSTIN_SELLER>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -433,7 +433,7 @@
       "special": false
     },
     "57571": {
-      "content": "<s_PO_NUMBER>",
+      "content": "<s_GST(7%)>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -441,7 +441,7 @@
       "special": false
     },
     "57572": {
-      "content": "</s_PO_NUMBER>",
+      "content": "</s_GST(7%)>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -449,7 +449,7 @@
       "special": false
     },
     "57573": {
-      "content": "<s_SELLER_SITE>",
+      "content": "<s_BILL_TO>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -457,7 +457,7 @@
       "special": false
     },
     "57574": {
-      "content": "</s_SELLER_SITE>",
+      "content": "</s_BILL_TO>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -465,7 +465,7 @@
       "special": false
     },
     "57575": {
-      "content": "<s_GST(1%)>",
+      "content": "<s_GST(9%)>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -473,7 +473,7 @@
       "special": false
     },
     "57576": {
-      "content": "</s_GST(1%)>",
+      "content": "</s_GST(9%)>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -481,7 +481,7 @@
       "special": false
     },
     "57577": {
-      "content": "<s_GST(20%)>",
+      "content": "<s_SEND_TO>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -489,7 +489,7 @@
       "special": false
     },
     "57578": {
-      "content": "</s_GST(20%)>",
+      "content": "</s_SEND_TO>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -497,102 +497,6 @@
       "special": false
     },
     "57579": {
-      "content": "<s_GST(18%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57580": {
-      "content": "</s_GST(18%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57581": {
-      "content": "<s_GST(12%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57582": {
-      "content": "</s_GST(12%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57583": {
-      "content": "<s_GST(5%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57584": {
-      "content": "</s_GST(5%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57585": {
-      "content": "<s_BILL_TO>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57586": {
-      "content": "</s_BILL_TO>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57587": {
-      "content": "<s_GST(7%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57588": {
-      "content": "</s_GST(7%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57589": {
-      "content": "<s_GST(9%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57590": {
-      "content": "</s_GST(9%)>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "57591": {
       "content": "<s_invoice>",
       "lstrip": false,
       "normalized": true,