Training done

added_tokens.json

@@ -0,0 +1,46 @@
+{
+ "</s_Qc>": 57564,
+ "</s_amount_due>": 57552,
+ "</s_broker_address>": 57542,
+ "</s_broker_memo_re>": 57562,
+ "</s_broker_name>": 57540,
+ "</s_copy_type>": 57534,
+ "</s_customer_address>": 57538,
+ "</s_customer_name>": 57536,
+ "</s_document_type>": 57554,
+ "</s_document_type_description>": 57532,
+ "</s_effective_date>": 57544,
+ "</s_effective_document_date>": 57546,
+ "</s_expiry_date>": 57548,
+ "</s_insurance_carrier>": 57526,
+ "</s_insurance_carrier_address>": 57530,
+ "</s_null>": 57558,
+ "</s_payment_schedule_date>": 57560,
+ "</s_policy_number>": 57528,
+ "</s_policy_type>": 57556,
+ "</s_premium>": 57550,
+ "<s_Qc>": 57563,
+ "<s_amount_due>": 57551,
+ "<s_broker_address>": 57541,
+ "<s_broker_memo_re>": 57561,
+ "<s_broker_name>": 57539,
+ "<s_copy_type>": 57533,
+ "<s_cord-v2>": 57565,
+ "<s_customer_address>": 57537,
+ "<s_customer_name>": 57535,
+ "<s_document_type>": 57553,
+ "<s_document_type_description>": 57531,
+ "<s_effective_date>": 57543,
+ "<s_effective_document_date>": 57545,
+ "<s_expiry_date>": 57547,
+ "<s_iitcdip>": 57523,
+ "<s_insurance_carrier>": 57525,
+ "<s_insurance_carrier_address>": 57529,
+ "<s_null>": 57557,
+ "<s_payment_schedule_date>": 57559,
+ "<s_policy_number>": 57527,
+ "<s_policy_type>": 57555,
+ "<s_premium>": 57549,
+ "<s_synthdog>": 57524,
+ "<sep/>": 57522
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+ "do_align_long_axis": false,
+ "do_normalize": true,
+ "do_pad": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_thumbnail": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "DonutImageProcessor",
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "processor_class": "DonutProcessor",
+ "resample": 2,
+ "rescale_factor": 0.00392156862745098,
+ "size": [
+ 960,
+ 1280
+ ]
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+ "additional_special_tokens": [
+ "<s_iitcdip>",
+ "<s_synthdog>"
+ ],
+ "bos_token": "<s>",
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": {
+ "__type": "AddedToken",
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "processor_class": "DonutProcessor",
+ "sep_token": "</s>",
+ "sp_model_kwargs": {},
+ "special_tokens_map_file": null,
+ "tokenizer_class": "XLMRobertaTokenizer",
+ "unk_token": "<unk>"
+}