End of training

README.md

@@ -12,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test
 
-This model is a fine-tuned version of [naver-clova-ix/donut-base-finetuned-cord-v2](https://huggingface.co/naver-clova-ix/donut-base-finetuned-cord-v2) on an unknown dataset.
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on an unknown dataset.
 
 ## Model description
 
@@ -32,12 +32,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 7
 
 ### Training results
 

added_tokens.json

@@ -7,6 +7,40 @@
   "</s_discountprice>": 57567,
   "</s_emoneyprice>": 57569,
   "</s_etc>": 57541,
+  "</s_h_bic>": 57643,
+  "</s_h_contactperson>": 57641,
+  "</s_h_creditorcity>": 57619,
+  "</s_h_creditorcountry>": 57617,
+  "</s_h_creditoriban>": 57615,
+  "</s_h_creditorname>": 57613,
+  "</s_h_creditorpostcode>": 57611,
+  "</s_h_creditorsalestaxid>": 57609,
+  "</s_h_creditorstreet>": 57607,
+  "</s_h_creditortaxid>": 57621,
+  "</s_h_currency1>": 57605,
+  "</s_h_deldate>": 57603,
+  "</s_h_deliverynotenumber>": 57631,
+  "</s_h_discount>": 57639,
+  "</s_h_documentdate>": 57601,
+  "</s_h_documenttype>": 57599,
+  "</s_h_extracharges>": 57597,
+  "</s_h_grossamount>": 57595,
+  "</s_h_invoicenumber>": 57593,
+  "</s_h_invoicerecipient>": 57591,
+  "</s_h_netamount1>": 57589,
+  "</s_h_ordernumber>": 57623,
+  "</s_h_paymentterms>": 57637,
+  "</s_h_receiptdate>": 57587,
+  "</s_h_recipientsalestaxid>": 57635,
+  "</s_h_taxamount1>": 57585,
+  "</s_h_taxamount2>": 57627,
+  "</s_h_taxamount3>": 57647,
+  "</s_h_taxbasisamount1>": 57583,
+  "</s_h_taxbasisamount2>": 57629,
+  "</s_h_taxrate1>": 57581,
+  "</s_h_taxrate2>": 57625,
+  "</s_h_taxrate3>": 57645,
+  "</s_h_web>": 57633,
   "</s_itemsubtotal>": 57577,
   "</s_menu>": 57525,
   "</s_menuqty_cnt>": 57555,
@@ -35,6 +69,40 @@
   "<s_discountprice>": 57568,
   "<s_emoneyprice>": 57570,
   "<s_etc>": 57542,
+  "<s_h_bic>": 57642,
+  "<s_h_contactperson>": 57640,
+  "<s_h_creditorcity>": 57618,
+  "<s_h_creditorcountry>": 57616,
+  "<s_h_creditoriban>": 57614,
+  "<s_h_creditorname>": 57612,
+  "<s_h_creditorpostcode>": 57610,
+  "<s_h_creditorsalestaxid>": 57608,
+  "<s_h_creditorstreet>": 57606,
+  "<s_h_creditortaxid>": 57620,
+  "<s_h_currency1>": 57604,
+  "<s_h_deldate>": 57602,
+  "<s_h_deliverynotenumber>": 57630,
+  "<s_h_discount>": 57638,
+  "<s_h_documentdate>": 57600,
+  "<s_h_documenttype>": 57598,
+  "<s_h_extracharges>": 57596,
+  "<s_h_grossamount>": 57594,
+  "<s_h_invoicenumber>": 57592,
+  "<s_h_invoicerecipient>": 57590,
+  "<s_h_netamount1>": 57588,
+  "<s_h_ordernumber>": 57622,
+  "<s_h_paymentterms>": 57636,
+  "<s_h_receiptdate>": 57586,
+  "<s_h_recipientsalestaxid>": 57634,
+  "<s_h_taxamount1>": 57584,
+  "<s_h_taxamount2>": 57626,
+  "<s_h_taxamount3>": 57646,
+  "<s_h_taxbasisamount1>": 57582,
+  "<s_h_taxbasisamount2>": 57628,
+  "<s_h_taxrate1>": 57580,
+  "<s_h_taxrate2>": 57624,
+  "<s_h_taxrate3>": 57644,
+  "<s_h_web>": 57632,
   "<s_iitcdip>": 57523,
   "<s_itemsubtotal>": 57578,
   "<s_menu>": 57526,

runs/Aug23_14-21-35_ip-172-31-42-230.eu-central-1.compute.internal/events.out.tfevents.1692800525.ip-172-31-42-230.eu-central-1.compute.internal.11141.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a540a2b59c6141a26005bae5905204faf81b62ea595119d1df5e88fded948e9c
-size 10732
+oid sha256:d4df5a31175231a11101aa2f9d40fa71334c06c05751de2d84fc425ecb448bf2
+size 11086

special_tokens_map.json

@@ -1,5 +1,73 @@
 {
   "additional_special_tokens": [
+    "<s_h_taxrate1>",
+    "</s_h_taxrate1>",
+    "<s_h_taxbasisamount1>",
+    "</s_h_taxbasisamount1>",
+    "<s_h_taxamount1>",
+    "</s_h_taxamount1>",
+    "<s_h_receiptdate>",
+    "</s_h_receiptdate>",
+    "<s_h_netamount1>",
+    "</s_h_netamount1>",
+    "<s_h_invoicerecipient>",
+    "</s_h_invoicerecipient>",
+    "<s_h_invoicenumber>",
+    "</s_h_invoicenumber>",
+    "<s_h_grossamount>",
+    "</s_h_grossamount>",
+    "<s_h_extracharges>",
+    "</s_h_extracharges>",
+    "<s_h_documenttype>",
+    "</s_h_documenttype>",
+    "<s_h_documentdate>",
+    "</s_h_documentdate>",
+    "<s_h_deldate>",
+    "</s_h_deldate>",
+    "<s_h_currency1>",
+    "</s_h_currency1>",
+    "<s_h_creditorstreet>",
+    "</s_h_creditorstreet>",
+    "<s_h_creditorsalestaxid>",
+    "</s_h_creditorsalestaxid>",
+    "<s_h_creditorpostcode>",
+    "</s_h_creditorpostcode>",
+    "<s_h_creditorname>",
+    "</s_h_creditorname>",
+    "<s_h_creditoriban>",
+    "</s_h_creditoriban>",
+    "<s_h_creditorcountry>",
+    "</s_h_creditorcountry>",
+    "<s_h_creditorcity>",
+    "</s_h_creditorcity>",
+    "<s_h_creditortaxid>",
+    "</s_h_creditortaxid>",
+    "<s_h_ordernumber>",
+    "</s_h_ordernumber>",
+    "<s_h_taxrate2>",
+    "</s_h_taxrate2>",
+    "<s_h_taxamount2>",
+    "</s_h_taxamount2>",
+    "<s_h_taxbasisamount2>",
+    "</s_h_taxbasisamount2>",
+    "<s_h_deliverynotenumber>",
+    "</s_h_deliverynotenumber>",
+    "<s_h_web>",
+    "</s_h_web>",
+    "<s_h_recipientsalestaxid>",
+    "</s_h_recipientsalestaxid>",
+    "<s_h_paymentterms>",
+    "</s_h_paymentterms>",
+    "<s_h_discount>",
+    "</s_h_discount>",
+    "<s_h_contactperson>",
+    "</s_h_contactperson>",
+    "<s_h_bic>",
+    "</s_h_bic>",
+    "<s_h_taxrate3>",
+    "</s_h_taxrate3>",
+    "<s_h_taxamount3>",
+    "</s_h_taxamount3>",
     "<s>",
     "</s>"
   ],

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -569,6 +583,618 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 57580,
+      "content": "<s_h_taxrate1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57581,
+      "content": "</s_h_taxrate1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57582,
+      "content": "<s_h_taxbasisamount1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57583,
+      "content": "</s_h_taxbasisamount1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57584,
+      "content": "<s_h_taxamount1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57585,
+      "content": "</s_h_taxamount1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57586,
+      "content": "<s_h_receiptdate>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57587,
+      "content": "</s_h_receiptdate>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57588,
+      "content": "<s_h_netamount1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57589,
+      "content": "</s_h_netamount1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57590,
+      "content": "<s_h_invoicerecipient>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57591,
+      "content": "</s_h_invoicerecipient>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57592,
+      "content": "<s_h_invoicenumber>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57593,
+      "content": "</s_h_invoicenumber>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57594,
+      "content": "<s_h_grossamount>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57595,
+      "content": "</s_h_grossamount>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57596,
+      "content": "<s_h_extracharges>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57597,
+      "content": "</s_h_extracharges>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57598,
+      "content": "<s_h_documenttype>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57599,
+      "content": "</s_h_documenttype>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57600,
+      "content": "<s_h_documentdate>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57601,
+      "content": "</s_h_documentdate>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57602,
+      "content": "<s_h_deldate>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57603,
+      "content": "</s_h_deldate>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57604,
+      "content": "<s_h_currency1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57605,
+      "content": "</s_h_currency1>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57606,
+      "content": "<s_h_creditorstreet>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57607,
+      "content": "</s_h_creditorstreet>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57608,
+      "content": "<s_h_creditorsalestaxid>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57609,
+      "content": "</s_h_creditorsalestaxid>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57610,
+      "content": "<s_h_creditorpostcode>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57611,
+      "content": "</s_h_creditorpostcode>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57612,
+      "content": "<s_h_creditorname>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57613,
+      "content": "</s_h_creditorname>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57614,
+      "content": "<s_h_creditoriban>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57615,
+      "content": "</s_h_creditoriban>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57616,
+      "content": "<s_h_creditorcountry>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57617,
+      "content": "</s_h_creditorcountry>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57618,
+      "content": "<s_h_creditorcity>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57619,
+      "content": "</s_h_creditorcity>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57620,
+      "content": "<s_h_creditortaxid>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57621,
+      "content": "</s_h_creditortaxid>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57622,
+      "content": "<s_h_ordernumber>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57623,
+      "content": "</s_h_ordernumber>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57624,
+      "content": "<s_h_taxrate2>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57625,
+      "content": "</s_h_taxrate2>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57626,
+      "content": "<s_h_taxamount2>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57627,
+      "content": "</s_h_taxamount2>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57628,
+      "content": "<s_h_taxbasisamount2>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57629,
+      "content": "</s_h_taxbasisamount2>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57630,
+      "content": "<s_h_deliverynotenumber>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57631,
+      "content": "</s_h_deliverynotenumber>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57632,
+      "content": "<s_h_web>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57633,
+      "content": "</s_h_web>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57634,
+      "content": "<s_h_recipientsalestaxid>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57635,
+      "content": "</s_h_recipientsalestaxid>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57636,
+      "content": "<s_h_paymentterms>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57637,
+      "content": "</s_h_paymentterms>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57638,
+      "content": "<s_h_discount>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57639,
+      "content": "</s_h_discount>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57640,
+      "content": "<s_h_contactperson>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57641,
+      "content": "</s_h_contactperson>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57642,
+      "content": "<s_h_bic>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57643,
+      "content": "</s_h_bic>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57644,
+      "content": "<s_h_taxrate3>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57645,
+      "content": "</s_h_taxrate3>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57646,
+      "content": "<s_h_taxamount3>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57647,
+      "content": "</s_h_taxamount3>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {