Training done
Browse files- added_tokens.json +19 -15
- tokenizer.json +50 -14
added_tokens.json
CHANGED
|
@@ -1,11 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"</s_income-w2-allocated-tips>":
|
| 3 |
-
"</s_income-w2-dependent-care-benefits>":
|
| 4 |
-
"</s_income-w2-
|
| 5 |
-
"</s_income-w2-employer-address-
|
| 6 |
-
"</s_income-w2-employer>":
|
| 7 |
-
"</s_income-w2-
|
| 8 |
-
"</s_income-w2-federal-
|
|
|
|
|
|
|
| 9 |
"</s_income-w2-fourteen-a-amount>": 57604,
|
| 10 |
"</s_income-w2-fourteen-a-code>": 57602,
|
| 11 |
"</s_income-w2-fourteen-b-amount>": 57600,
|
|
@@ -47,13 +49,15 @@
|
|
| 47 |
"</s_income-w2-twelve-d-partTwo>": 57528,
|
| 48 |
"</s_income-w2-wages>": 57526,
|
| 49 |
"<s_iitcdip>": 57523,
|
| 50 |
-
"<s_income-w2-allocated-tips>":
|
| 51 |
-
"<s_income-w2-dependent-care-benefits>":
|
| 52 |
-
"<s_income-w2-
|
| 53 |
-
"<s_income-w2-employer-address-
|
| 54 |
-
"<s_income-w2-employer>":
|
| 55 |
-
"<s_income-w2-
|
| 56 |
-
"<s_income-w2-federal-
|
|
|
|
|
|
|
| 57 |
"<s_income-w2-fourteen-a-amount>": 57603,
|
| 58 |
"<s_income-w2-fourteen-a-code>": 57601,
|
| 59 |
"<s_income-w2-fourteen-b-amount>": 57599,
|
|
@@ -96,5 +100,5 @@
|
|
| 96 |
"<s_income-w2-wages>": 57525,
|
| 97 |
"<s_synthdog>": 57524,
|
| 98 |
"<sep/>": 57522,
|
| 99 |
-
"<tax_doc_parse>":
|
| 100 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"</s_income-w2-allocated-tips>": 57622,
|
| 3 |
+
"</s_income-w2-dependent-care-benefits>": 57620,
|
| 4 |
+
"</s_income-w2-employee-ssn>": 57618,
|
| 5 |
+
"</s_income-w2-employer-address-line1>": 57614,
|
| 6 |
+
"</s_income-w2-employer-address-line2>": 57612,
|
| 7 |
+
"</s_income-w2-employer>": 57616,
|
| 8 |
+
"</s_income-w2-federal-id>": 57610,
|
| 9 |
+
"</s_income-w2-federal-income-tax-withheld>": 57608,
|
| 10 |
+
"</s_income-w2-form-year>": 57606,
|
| 11 |
"</s_income-w2-fourteen-a-amount>": 57604,
|
| 12 |
"</s_income-w2-fourteen-a-code>": 57602,
|
| 13 |
"</s_income-w2-fourteen-b-amount>": 57600,
|
|
|
|
| 49 |
"</s_income-w2-twelve-d-partTwo>": 57528,
|
| 50 |
"</s_income-w2-wages>": 57526,
|
| 51 |
"<s_iitcdip>": 57523,
|
| 52 |
+
"<s_income-w2-allocated-tips>": 57621,
|
| 53 |
+
"<s_income-w2-dependent-care-benefits>": 57619,
|
| 54 |
+
"<s_income-w2-employee-ssn>": 57617,
|
| 55 |
+
"<s_income-w2-employer-address-line1>": 57613,
|
| 56 |
+
"<s_income-w2-employer-address-line2>": 57611,
|
| 57 |
+
"<s_income-w2-employer>": 57615,
|
| 58 |
+
"<s_income-w2-federal-id>": 57609,
|
| 59 |
+
"<s_income-w2-federal-income-tax-withheld>": 57607,
|
| 60 |
+
"<s_income-w2-form-year>": 57605,
|
| 61 |
"<s_income-w2-fourteen-a-amount>": 57603,
|
| 62 |
"<s_income-w2-fourteen-a-code>": 57601,
|
| 63 |
"<s_income-w2-fourteen-b-amount>": 57599,
|
|
|
|
| 100 |
"<s_income-w2-wages>": 57525,
|
| 101 |
"<s_synthdog>": 57524,
|
| 102 |
"<sep/>": 57522,
|
| 103 |
+
"<tax_doc_parse>": 57623
|
| 104 |
}
|
tokenizer.json
CHANGED
|
@@ -811,7 +811,7 @@
|
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"id": 57605,
|
| 814 |
-
"content": "<s_income-w2-
|
| 815 |
"single_word": false,
|
| 816 |
"lstrip": false,
|
| 817 |
"rstrip": false,
|
|
@@ -820,7 +820,7 @@
|
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"id": 57606,
|
| 823 |
-
"content": "</s_income-w2-
|
| 824 |
"single_word": false,
|
| 825 |
"lstrip": false,
|
| 826 |
"rstrip": false,
|
|
@@ -829,7 +829,7 @@
|
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"id": 57607,
|
| 832 |
-
"content": "<s_income-w2-federal-
|
| 833 |
"single_word": false,
|
| 834 |
"lstrip": false,
|
| 835 |
"rstrip": false,
|
|
@@ -838,7 +838,7 @@
|
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"id": 57608,
|
| 841 |
-
"content": "</s_income-w2-federal-
|
| 842 |
"single_word": false,
|
| 843 |
"lstrip": false,
|
| 844 |
"rstrip": false,
|
|
@@ -847,7 +847,7 @@
|
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"id": 57609,
|
| 850 |
-
"content": "<s_income-w2-
|
| 851 |
"single_word": false,
|
| 852 |
"lstrip": false,
|
| 853 |
"rstrip": false,
|
|
@@ -856,7 +856,7 @@
|
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"id": 57610,
|
| 859 |
-
"content": "</s_income-w2-
|
| 860 |
"single_word": false,
|
| 861 |
"lstrip": false,
|
| 862 |
"rstrip": false,
|
|
@@ -865,7 +865,7 @@
|
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"id": 57611,
|
| 868 |
-
"content": "<s_income-w2-employer-address-
|
| 869 |
"single_word": false,
|
| 870 |
"lstrip": false,
|
| 871 |
"rstrip": false,
|
|
@@ -874,7 +874,7 @@
|
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"id": 57612,
|
| 877 |
-
"content": "</s_income-w2-employer-address-
|
| 878 |
"single_word": false,
|
| 879 |
"lstrip": false,
|
| 880 |
"rstrip": false,
|
|
@@ -883,7 +883,7 @@
|
|
| 883 |
},
|
| 884 |
{
|
| 885 |
"id": 57613,
|
| 886 |
-
"content": "<s_income-w2-employer>",
|
| 887 |
"single_word": false,
|
| 888 |
"lstrip": false,
|
| 889 |
"rstrip": false,
|
|
@@ -892,7 +892,7 @@
|
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"id": 57614,
|
| 895 |
-
"content": "</s_income-w2-employer>",
|
| 896 |
"single_word": false,
|
| 897 |
"lstrip": false,
|
| 898 |
"rstrip": false,
|
|
@@ -901,7 +901,7 @@
|
|
| 901 |
},
|
| 902 |
{
|
| 903 |
"id": 57615,
|
| 904 |
-
"content": "<s_income-w2-
|
| 905 |
"single_word": false,
|
| 906 |
"lstrip": false,
|
| 907 |
"rstrip": false,
|
|
@@ -910,7 +910,7 @@
|
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"id": 57616,
|
| 913 |
-
"content": "</s_income-w2-
|
| 914 |
"single_word": false,
|
| 915 |
"lstrip": false,
|
| 916 |
"rstrip": false,
|
|
@@ -919,7 +919,7 @@
|
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"id": 57617,
|
| 922 |
-
"content": "<s_income-w2-
|
| 923 |
"single_word": false,
|
| 924 |
"lstrip": false,
|
| 925 |
"rstrip": false,
|
|
@@ -928,7 +928,7 @@
|
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"id": 57618,
|
| 931 |
-
"content": "</s_income-w2-
|
| 932 |
"single_word": false,
|
| 933 |
"lstrip": false,
|
| 934 |
"rstrip": false,
|
|
@@ -937,6 +937,42 @@
|
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"id": 57619,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 940 |
"content": "<tax_doc_parse>",
|
| 941 |
"single_word": false,
|
| 942 |
"lstrip": false,
|
|
|
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"id": 57605,
|
| 814 |
+
"content": "<s_income-w2-form-year>",
|
| 815 |
"single_word": false,
|
| 816 |
"lstrip": false,
|
| 817 |
"rstrip": false,
|
|
|
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"id": 57606,
|
| 823 |
+
"content": "</s_income-w2-form-year>",
|
| 824 |
"single_word": false,
|
| 825 |
"lstrip": false,
|
| 826 |
"rstrip": false,
|
|
|
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"id": 57607,
|
| 832 |
+
"content": "<s_income-w2-federal-income-tax-withheld>",
|
| 833 |
"single_word": false,
|
| 834 |
"lstrip": false,
|
| 835 |
"rstrip": false,
|
|
|
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"id": 57608,
|
| 841 |
+
"content": "</s_income-w2-federal-income-tax-withheld>",
|
| 842 |
"single_word": false,
|
| 843 |
"lstrip": false,
|
| 844 |
"rstrip": false,
|
|
|
|
| 847 |
},
|
| 848 |
{
|
| 849 |
"id": 57609,
|
| 850 |
+
"content": "<s_income-w2-federal-id>",
|
| 851 |
"single_word": false,
|
| 852 |
"lstrip": false,
|
| 853 |
"rstrip": false,
|
|
|
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"id": 57610,
|
| 859 |
+
"content": "</s_income-w2-federal-id>",
|
| 860 |
"single_word": false,
|
| 861 |
"lstrip": false,
|
| 862 |
"rstrip": false,
|
|
|
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"id": 57611,
|
| 868 |
+
"content": "<s_income-w2-employer-address-line2>",
|
| 869 |
"single_word": false,
|
| 870 |
"lstrip": false,
|
| 871 |
"rstrip": false,
|
|
|
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"id": 57612,
|
| 877 |
+
"content": "</s_income-w2-employer-address-line2>",
|
| 878 |
"single_word": false,
|
| 879 |
"lstrip": false,
|
| 880 |
"rstrip": false,
|
|
|
|
| 883 |
},
|
| 884 |
{
|
| 885 |
"id": 57613,
|
| 886 |
+
"content": "<s_income-w2-employer-address-line1>",
|
| 887 |
"single_word": false,
|
| 888 |
"lstrip": false,
|
| 889 |
"rstrip": false,
|
|
|
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"id": 57614,
|
| 895 |
+
"content": "</s_income-w2-employer-address-line1>",
|
| 896 |
"single_word": false,
|
| 897 |
"lstrip": false,
|
| 898 |
"rstrip": false,
|
|
|
|
| 901 |
},
|
| 902 |
{
|
| 903 |
"id": 57615,
|
| 904 |
+
"content": "<s_income-w2-employer>",
|
| 905 |
"single_word": false,
|
| 906 |
"lstrip": false,
|
| 907 |
"rstrip": false,
|
|
|
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"id": 57616,
|
| 913 |
+
"content": "</s_income-w2-employer>",
|
| 914 |
"single_word": false,
|
| 915 |
"lstrip": false,
|
| 916 |
"rstrip": false,
|
|
|
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"id": 57617,
|
| 922 |
+
"content": "<s_income-w2-employee-ssn>",
|
| 923 |
"single_word": false,
|
| 924 |
"lstrip": false,
|
| 925 |
"rstrip": false,
|
|
|
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"id": 57618,
|
| 931 |
+
"content": "</s_income-w2-employee-ssn>",
|
| 932 |
"single_word": false,
|
| 933 |
"lstrip": false,
|
| 934 |
"rstrip": false,
|
|
|
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"id": 57619,
|
| 940 |
+
"content": "<s_income-w2-dependent-care-benefits>",
|
| 941 |
+
"single_word": false,
|
| 942 |
+
"lstrip": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"normalized": true,
|
| 945 |
+
"special": false
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"id": 57620,
|
| 949 |
+
"content": "</s_income-w2-dependent-care-benefits>",
|
| 950 |
+
"single_word": false,
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"rstrip": false,
|
| 953 |
+
"normalized": true,
|
| 954 |
+
"special": false
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"id": 57621,
|
| 958 |
+
"content": "<s_income-w2-allocated-tips>",
|
| 959 |
+
"single_word": false,
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"normalized": true,
|
| 963 |
+
"special": false
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"id": 57622,
|
| 967 |
+
"content": "</s_income-w2-allocated-tips>",
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"lstrip": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"normalized": true,
|
| 972 |
+
"special": false
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"id": 57623,
|
| 976 |
"content": "<tax_doc_parse>",
|
| 977 |
"single_word": false,
|
| 978 |
"lstrip": false,
|