End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: naver-clova-ix/donut-base
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut-base-sroie
+  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-sroie
+
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) 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: 2e-05
+- 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: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</s_건물>": 57536,
+  "</s_계약금>": 57554,
+  "</s_구조・용도>": 57538,
+  "</s_금액>": 57546,
+  "</s_면적>": 57530,
+  "</s_보증금>": 57552,
+  "</s_소재지>": 57534,
+  "</s_임차할부분>": 57532,
+  "</s_입금계좌>": 57544,
+  "</s_잔금>": 57550,
+  "</s_중도금>": 57548,
+  "</s_지급일>": 57542,
+  "</s_지목>": 57528,
+  "</s_토지>": 57526,
+  "</s_환산보증금>": 57540,
+  "<s_iitcdip>": 57523,
+  "<s_synthdog>": 57524,
+  "<s_건물>": 57535,
+  "<s_계약금>": 57553,
+  "<s_구조・용도>": 57537,
+  "<s_금액>": 57545,
+  "<s_면적>": 57529,
+  "<s_보증금>": 57551,
+  "<s_소재지>": 57533,
+  "<s_임차할부분>": 57531,
+  "<s_입금계좌>": 57543,
+  "<s_잔금>": 57549,
+  "<s_중도금>": 57547,
+  "<s_지급일>": 57541,
+  "<s_지목>": 57527,
+  "<s_토지>": 57525,
+  "<s_환산보증금>": 57539,
+  "<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": "4.32.1"
+}

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
+  ]
+}

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 +1,49 @@
+{
+  "additional_special_tokens": [
+    "<s_토지>",
+    "</s_토지>",
+    "<s_지목>",
+    "</s_지목>",
+    "<s_면적>",
+    "</s_면적>",
+    "<s_임차할부분>",
+    "</s_임차할부분>",
+    "<s_소재지>",
+    "</s_소재지>",
+    "<s_건물>",
+    "</s_건물>",
+    "<s_구조・용도>",
+    "</s_구조・용도>",
+    "<s_환산보증금>",
+    "</s_환산보증금>",
+    "<s_지급일>",
+    "</s_지급일>",
+    "<s_입금계좌>",
+    "</s_입금계좌>",
+    "<s_금액>",
+    "</s_금액>",
+    "<s_중도금>",
+    "</s_중도금>",
+    "<s_잔금>",
+    "</s_잔금>",
+    "<s_보증금>",
+    "</s_보증금>",
+    "<s_계약금>",
+    "</s_계약금>",
+    "<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>"
+}