Upload 10 files

added_tokens.json

@@ -0,0 +1,137 @@
+{
+  "</s_cashprice>": 57549,
+  "</s_changeprice>": 57551,
+  "</s_cnt>": 57529,
+  "</s_creditcardprice>": 57563,
+  "</s_discount_price>": 57557,
+  "</s_discountprice>": 57567,
+  "</s_emoneyprice>": 57569,
+  "</s_etc>": 57541,
+  "</s_h_bic>": 57638,
+  "</s_h_contactperson>": 57632,
+  "</s_h_creditorcity>": 57604,
+  "</s_h_creditorcountry>": 57612,
+  "</s_h_creditoriban>": 57606,
+  "</s_h_creditorname>": 57614,
+  "</s_h_creditorpobox>": 57648,
+  "</s_h_creditorpostcode>": 57592,
+  "</s_h_creditorsalestaxid>": 57596,
+  "</s_h_creditorsearch>": 57652,
+  "</s_h_creditorstreet>": 57590,
+  "</s_h_creditortaxid>": 57620,
+  "</s_h_currency1>": 57602,
+  "</s_h_deldate>": 57610,
+  "</s_h_deliverynotenumber>": 57630,
+  "</s_h_discount>": 57642,
+  "</s_h_documentdate>": 57600,
+  "</s_h_documenttype>": 57582,
+  "</s_h_extracharges>": 57588,
+  "</s_h_grossamount>": 57580,
+  "</s_h_invoicenumber>": 57586,
+  "</s_h_invoicerecipient>": 57616,
+  "</s_h_netamount1>": 57594,
+  "</s_h_ordernumber>": 57622,
+  "</s_h_paymentterms>": 57634,
+  "</s_h_receiptdate>": 57608,
+  "</s_h_recipientsalestaxid>": 57636,
+  "</s_h_recipienttaxid>": 57654,
+  "</s_h_taxamount1>": 57618,
+  "</s_h_taxamount2>": 57626,
+  "</s_h_taxamount3>": 57644,
+  "</s_h_taxbasisamount1>": 57598,
+  "</s_h_taxbasisamount2>": 57628,
+  "</s_h_taxbasisamount3>": 57650,
+  "</s_h_taxrate1>": 57584,
+  "</s_h_taxrate2>": 57624,
+  "</s_h_taxrate3>": 57646,
+  "</s_h_web>": 57640,
+  "</s_itemsubtotal>": 57577,
+  "</s_menu>": 57525,
+  "</s_menuqty_cnt>": 57555,
+  "</s_menutype_cnt>": 57553,
+  "</s_nm>": 57527,
+  "</s_num>": 57565,
+  "</s_othersvc_price>": 57573,
+  "</s_price>": 57531,
+  "</s_service_price>": 57537,
+  "</s_sub>": 57547,
+  "</s_sub_total>": 57533,
+  "</s_subtotal_price>": 57535,
+  "</s_tax_price>": 57539,
+  "</s_total>": 57543,
+  "</s_total_etc>": 57561,
+  "</s_total_price>": 57545,
+  "</s_unitprice>": 57559,
+  "</s_vatyn>": 57575,
+  "</s_void_menu>": 57571,
+  "<s_cashprice>": 57550,
+  "<s_changeprice>": 57552,
+  "<s_cnt>": 57530,
+  "<s_cord-v2>": 57579,
+  "<s_creditcardprice>": 57564,
+  "<s_discount_price>": 57558,
+  "<s_discountprice>": 57568,
+  "<s_emoneyprice>": 57570,
+  "<s_etc>": 57542,
+  "<s_h_bic>": 57639,
+  "<s_h_contactperson>": 57633,
+  "<s_h_creditorcity>": 57605,
+  "<s_h_creditorcountry>": 57613,
+  "<s_h_creditoriban>": 57607,
+  "<s_h_creditorname>": 57615,
+  "<s_h_creditorpobox>": 57649,
+  "<s_h_creditorpostcode>": 57593,
+  "<s_h_creditorsalestaxid>": 57597,
+  "<s_h_creditorsearch>": 57653,
+  "<s_h_creditorstreet>": 57591,
+  "<s_h_creditortaxid>": 57621,
+  "<s_h_currency1>": 57603,
+  "<s_h_deldate>": 57611,
+  "<s_h_deliverynotenumber>": 57631,
+  "<s_h_discount>": 57643,
+  "<s_h_documentdate>": 57601,
+  "<s_h_documenttype>": 57583,
+  "<s_h_extracharges>": 57589,
+  "<s_h_grossamount>": 57581,
+  "<s_h_invoicenumber>": 57587,
+  "<s_h_invoicerecipient>": 57617,
+  "<s_h_netamount1>": 57595,
+  "<s_h_ordernumber>": 57623,
+  "<s_h_paymentterms>": 57635,
+  "<s_h_receiptdate>": 57609,
+  "<s_h_recipientsalestaxid>": 57637,
+  "<s_h_recipienttaxid>": 57655,
+  "<s_h_taxamount1>": 57619,
+  "<s_h_taxamount2>": 57627,
+  "<s_h_taxamount3>": 57645,
+  "<s_h_taxbasisamount1>": 57599,
+  "<s_h_taxbasisamount2>": 57629,
+  "<s_h_taxbasisamount3>": 57651,
+  "<s_h_taxrate1>": 57585,
+  "<s_h_taxrate2>": 57625,
+  "<s_h_taxrate3>": 57647,
+  "<s_h_web>": 57641,
+  "<s_iitcdip>": 57523,
+  "<s_invoice_dataset_large_cleaned_2>": 57656,
+  "<s_itemsubtotal>": 57578,
+  "<s_menu>": 57526,
+  "<s_menuqty_cnt>": 57556,
+  "<s_menutype_cnt>": 57554,
+  "<s_nm>": 57528,
+  "<s_num>": 57566,
+  "<s_othersvc_price>": 57574,
+  "<s_price>": 57532,
+  "<s_service_price>": 57538,
+  "<s_sub>": 57548,
+  "<s_sub_total>": 57534,
+  "<s_subtotal_price>": 57536,
+  "<s_synthdog>": 57524,
+  "<s_tax_price>": 57540,
+  "<s_total>": 57544,
+  "<s_total_etc>": 57562,
+  "<s_total_price>": 57546,
+  "<s_unitprice>": 57560,
+  "<s_vatyn>": 57576,
+  "<s_void_menu>": 57572,
+  "<sep/>": 57522
+}

artifacts.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002af47ed9323d85605a541017a3714fd7fa4a8220d14e35132dde57f8e23631
+size 1609929307

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base-finetuned-cord-v2",
+  "align_long_axis": false,
+  "architectures": [
+    "DonutModel"
+  ],
+  "decoder_layer": 4,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "input_size": [
+    960,
+    1280
+  ],
+  "max_length": 768,
+  "max_position_embeddings": 768,
+  "model_type": "donut",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "window_size": 10
+}

config.yaml

@@ -0,0 +1,29 @@
+resume_from_checkpoint_path: None
+result_path: './result'
+pretrained_model_name_or_path: 'naver-clova-ix/donut-base-finetuned-cord-v2'
+dataset_name_or_paths: 
+  - 'verbrannter/invoice_dataset_large_cleaned_2'
+sort_json_key: False
+train_batch_sizes: 
+  - 2
+val_batch_sizes: 
+  - 1
+input_size: 
+  - 960
+  - 1280
+max_length: 768
+align_long_axis: False
+num_nodes: 1
+seed: 2022
+lr: 3e-05
+warmup_steps: 150
+num_training_samples_per_epoch: 500
+max_epochs: 15
+max_steps: -1
+num_workers: 256
+val_check_interval: 1.0
+check_val_every_n_epoch: 3
+gradient_clip_val: 1.0
+verbose: True
+exp_name: 'train_cord'
+exp_version: '20230816_221233'

events.out.tfevents.1692227373.ip-172-31-42-230.eu-central-1.compute.internal

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1363a6ef38f820978d0a17300cda7a4bf58fa506b520a906c9e5261acbb2b8
+size 451377

hparams.yaml

@@ -0,0 +1 @@
+{}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37492bde687b424bf705794c0e7901a895aa573a504a8ec7e3fb403613a620d0
+size 858865985

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 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<s_invoice_dataset_large_cleaned_2>"
+  ],
+  "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>",
+  "from_slow": true,
+  "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": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}