End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut-base-ocr4
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# donut-base-ocr4
+
+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 the imagefolder dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.29.2
+- Pytorch 2.0.1+cu118
+- Datasets 2.13.1
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,88 @@
+{
+  "</s_Date>": 57605,
+  "</s_HT_amount>": 57603,
+  "</s_ICE>": 57601,
+  "</s_TAX>": 57599,
+  "</s_Total_amount>": 57597,
+  "</s_address>": 57607,
+  "</s_adress>": 57595,
+  "</s_cashprice>": 57549,
+  "</s_changeprice>": 57551,
+  "</s_client>": 57593,
+  "</s_cnt>": 57529,
+  "</s_creditcardprice>": 57563,
+  "</s_discount_price>": 57557,
+  "</s_discountprice>": 57567,
+  "</s_domain>": 57591,
+  "</s_emoneyprice>": 57569,
+  "</s_etc>": 57541,
+  "</s_invoice_no>": 57589,
+  "</s_item>": 57587,
+  "</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_phone>": 57585,
+  "</s_price>": 57531,
+  "</s_quantity>": 57583,
+  "</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_unit_amount>": 57581,
+  "</s_unitprice>": 57559,
+  "</s_vatyn>": 57575,
+  "</s_void_menu>": 57571,
+  "<s_Date>": 57604,
+  "<s_HT_amount>": 57602,
+  "<s_ICE>": 57600,
+  "<s_TAX>": 57598,
+  "<s_Total_amount>": 57596,
+  "<s_address>": 57606,
+  "<s_adress>": 57594,
+  "<s_cashprice>": 57550,
+  "<s_changeprice>": 57552,
+  "<s_client>": 57592,
+  "<s_cnt>": 57530,
+  "<s_cord-v2>": 57579,
+  "<s_creditcardprice>": 57564,
+  "<s_discount_price>": 57558,
+  "<s_discountprice>": 57568,
+  "<s_domain>": 57590,
+  "<s_emoneyprice>": 57570,
+  "<s_etc>": 57542,
+  "<s_iitcdip>": 57523,
+  "<s_invoice_no>": 57588,
+  "<s_item>": 57586,
+  "<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_phone>": 57584,
+  "<s_price>": 57532,
+  "<s_quantity>": 57582,
+  "<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_unit_amount>": 57580,
+  "<s_unitprice>": 57560,
+  "<s_vatyn>": 57576,
+  "<s_void_menu>": 57572,
+  "<sep/>": 57522
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.29.2"
+}

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": [
+    720,
+    960
+  ]
+}

runs/Jul05_18-38-04_363594b81848/events.out.tfevents.1688582296.363594b81848.262.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755ff5584bf2394604d5f401ac0da48083c5e1720feeeb41427927f4f99a7b65
-size 26276
+oid sha256:c3f3f16830dce96acceeebc35e94b56d89c0a441c9bc0d2a41121c1cdcd23e2b
+size 26624

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 +1,47 @@
+{
+  "additional_special_tokens": [
+    "<s_unit_amount>",
+    "</s_unit_amount>",
+    "<s_quantity>",
+    "</s_quantity>",
+    "<s_phone>",
+    "</s_phone>",
+    "<s_item>",
+    "</s_item>",
+    "<s_invoice_no>",
+    "</s_invoice_no>",
+    "<s_domain>",
+    "</s_domain>",
+    "<s_client>",
+    "</s_client>",
+    "<s_adress>",
+    "</s_adress>",
+    "<s_Total_amount>",
+    "</s_Total_amount>",
+    "<s_TAX>",
+    "</s_TAX>",
+    "<s_ICE>",
+    "</s_ICE>",
+    "<s_HT_amount>",
+    "</s_HT_amount>",
+    "<s_Date>",
+    "</s_Date>",
+    "<s_address>",
+    "</s_address>",
+    "<s>",
+    "</s>"
+  ],
+  "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 +1,21 @@
+{
+  "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": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}