Upload 11 files

added_tokens.json

@@ -0,0 +1,82 @@
+{
+  "</s_cashprice>": 57549,
+  "</s_changeprice>": 57551,
+  "</s_cnt>": 57529,
+  "</s_creditcardprice>": 57563,
+  "</s_customer_party_legal_id>": 57584,
+  "</s_discount_price>": 57557,
+  "</s_discountprice>": 57567,
+  "</s_document_currency_code>": 57588,
+  "</s_emoneyprice>": 57569,
+  "</s_etc>": 57541,
+  "</s_financial_account>": 57592,
+  "</s_invoice_number>": 57582,
+  "</s_issue_date>": 57580,
+  "</s_itemsubtotal>": 57577,
+  "</s_menu>": 57525,
+  "</s_menuqty_cnt>": 57555,
+  "</s_menutype_cnt>": 57553,
+  "</s_nm>": 57527,
+  "</s_num>": 57565,
+  "</s_order_reference>": 57598,
+  "</s_othersvc_price>": 57573,
+  "</s_payable_amount>": 57590,
+  "</s_price>": 57531,
+  "</s_service_price>": 57537,
+  "</s_sub>": 57547,
+  "</s_sub_total>": 57533,
+  "</s_subtotal_price>": 57535,
+  "</s_supplier_party_legal_id>": 57594,
+  "</s_tax_amount>": 57586,
+  "</s_tax_exclusive_amount>": 57596,
+  "</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_customer_party_legal_id>": 57585,
+  "<s_discount_price>": 57558,
+  "<s_discountprice>": 57568,
+  "<s_document_currency_code>": 57589,
+  "<s_donut_24_6_24>": 57600,
+  "<s_donut_batch1_8_7_24>": 57601,
+  "<s_emoneyprice>": 57570,
+  "<s_etc>": 57542,
+  "<s_financial_account>": 57593,
+  "<s_iitcdip>": 57523,
+  "<s_invoice_number>": 57583,
+  "<s_issue_date>": 57581,
+  "<s_itemsubtotal>": 57578,
+  "<s_menu>": 57526,
+  "<s_menuqty_cnt>": 57556,
+  "<s_menutype_cnt>": 57554,
+  "<s_nm>": 57528,
+  "<s_num>": 57566,
+  "<s_order_reference>": 57599,
+  "<s_othersvc_price>": 57574,
+  "<s_payable_amount>": 57591,
+  "<s_price>": 57532,
+  "<s_service_price>": 57538,
+  "<s_sub>": 57548,
+  "<s_sub_total>": 57534,
+  "<s_subtotal_price>": 57536,
+  "<s_supplier_party_legal_id>": 57595,
+  "<s_synthdog>": 57524,
+  "<s_tax_amount>": 57587,
+  "<s_tax_exclusive_amount>": 57597,
+  "<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 sha256:6f7f792baf2201e85de62eef77c531f3952bb06812bff5a30f06acfce903b504
+size 1609478737

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "Altimis/donut_int",
+  "align_long_axis": false,
+  "architectures": [
+    "MegaBrainDonut"
+  ],
+  "decoder_layer": 4,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "input_size": [
+    1280,
+    1920
+  ],
+  "max_length": 768,
+  "max_position_embeddings": 768,
+  "model_type": "donut",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "window_size": 10
+}

config.yaml

@@ -0,0 +1,29 @@
+resume_from_checkpoint_path: None
+result_path: 'donut/result'
+pretrained_model_name_or_path: 'Altimis/donut_int'
+dataset_name_or_paths: 
+  - 'gdrive/MyDrive/konta-backup/konta_experiments/donut_batch1_8_7_24'
+sort_json_key: False
+train_batch_sizes: 
+  - 2
+val_batch_sizes: 
+  - 1
+input_size: 
+  - 1280
+  - 1920
+max_length: 768
+align_long_axis: False
+num_nodes: 1
+seed: 2022
+lr: 3e-05
+warmup_steps: 400
+num_training_samples_per_epoch: 800
+max_epochs: 30
+max_steps: -1
+num_workers: 2
+val_check_interval: 1.0
+check_val_every_n_epoch: 3
+gradient_clip_val: 1.0
+verbose: True
+exp_name: 'train_cord_finetune_2'
+exp_version: '20240708_214424'

events.out.tfevents.1720475117.1312a6b6c0a4.625.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34019c81056cb81f0072bed56b37ee7c6896db45e223d2894ec845b70ee29416
+size 46244

hparams.yaml

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

model_checkpoint.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3377d1065928e117326747560818af90164ed87b7132d48084b261f0681b9702
+size 1609486822

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986c19e3655bd40d24c4ba9a5bbf3c558a44326f754eb867f2a28d00586dbef7
+size 910969990

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_donut_batch1_8_7_24>"
+  ],
+  "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 +1,23 @@
+{
+  "bos_token": "<s>",
+  "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,
+  "name_or_path": "Altimis/donut_int",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}