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-test
+  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-test
+
+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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,36 @@
+{
+  "</s>": 2,
+  "</s_Consignee>": 57536,
+  "</s_Consignee_Country>": 57533,
+  "</s_Consignor>": 57549,
+  "</s_Consignor_Country>": 57535,
+  "</s_Goods_Description>": 57541,
+  "</s_Marks>": 57548,
+  "</s_Notify>": 57540,
+  "</s_Notify_Country>": 57529,
+  "</s_Second_Notify>": 57546,
+  "</s_Second_Notify_Country>": 57532,
+  "</s_Total_Packages>": 57550,
+  "</s_Total_Volume>": 57547,
+  "</s_Total_Weight>": 57544,
+  "<mask>": 57521,
+  "<pad>": 1,
+  "<s>": 0,
+  "<s_Consignee>": 57545,
+  "<s_Consignee_Country>": 57528,
+  "<s_Consignor>": 57530,
+  "<s_Consignor_Country>": 57527,
+  "<s_Goods_Description>": 57534,
+  "<s_Marks>": 57538,
+  "<s_Notify>": 57526,
+  "<s_Notify_Country>": 57531,
+  "<s_Second_Notify>": 57542,
+  "<s_Second_Notify_Country>": 57537,
+  "<s_Total_Packages>": 57525,
+  "<s_Total_Volume>": 57543,
+  "<s_Total_Weight>": 57539,
+  "<s_iitcdip>": 57523,
+  "<s_synthdog>": 57524,
+  "<sep/>": 57522,
+  "<unk>": 3
+}

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": "4.34.0"
+}

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 +1,41 @@
+{
+  "additional_special_tokens": [
+    "<s_iitcdip>",
+    "<s_synthdog>",
+    "<s_Total_Packages>",
+    "<s_Notify>",
+    "<s_Consignor_Country>",
+    "<s_Consignee_Country>",
+    "</s_Notify_Country>",
+    "<s_Consignor>",
+    "<s_Notify_Country>",
+    "</s_Second_Notify_Country>",
+    "</s_Consignee_Country>",
+    "<s_Goods_Description>",
+    "</s_Consignor_Country>",
+    "</s_Consignee>",
+    "<s_Second_Notify_Country>",
+    "<s_Marks>",
+    "<s>",
+    "<s_Total_Weight>",
+    "</s_Notify>",
+    "</s_Goods_Description>",
+    "<s_Second_Notify>",
+    "<s_Total_Volume>",
+    "</s_Total_Weight>",
+    "</s>",
+    "<s_Consignee>",
+    "</s_Second_Notify>",
+    "</s_Total_Volume>",
+    "</s_Marks>",
+    "</s_Consignor>",
+    "</s_Total_Packages>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,320 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57521": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57522": {
+      "content": "<sep/>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57523": {
+      "content": "<s_iitcdip>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57524": {
+      "content": "<s_synthdog>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57525": {
+      "content": "<s_Total_Packages>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57526": {
+      "content": "<s_Notify>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57527": {
+      "content": "<s_Consignor_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57528": {
+      "content": "<s_Consignee_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57529": {
+      "content": "</s_Notify_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57530": {
+      "content": "<s_Consignor>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57531": {
+      "content": "<s_Notify_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57532": {
+      "content": "</s_Second_Notify_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57533": {
+      "content": "</s_Consignee_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57534": {
+      "content": "<s_Goods_Description>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57535": {
+      "content": "</s_Consignor_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57536": {
+      "content": "</s_Consignee>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57537": {
+      "content": "<s_Second_Notify_Country>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57538": {
+      "content": "<s_Marks>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57539": {
+      "content": "<s_Total_Weight>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57540": {
+      "content": "</s_Notify>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57541": {
+      "content": "</s_Goods_Description>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57542": {
+      "content": "<s_Second_Notify>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57543": {
+      "content": "<s_Total_Volume>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57544": {
+      "content": "</s_Total_Weight>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57545": {
+      "content": "<s_Consignee>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57546": {
+      "content": "</s_Second_Notify>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57547": {
+      "content": "</s_Total_Volume>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57548": {
+      "content": "</s_Marks>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57549": {
+      "content": "</s_Consignor>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "57550": {
+      "content": "</s_Total_Packages>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s_iitcdip>",
+    "<s_synthdog>",
+    "<s_Total_Packages>",
+    "<s_Notify>",
+    "<s_Consignor_Country>",
+    "<s_Consignee_Country>",
+    "</s_Notify_Country>",
+    "<s_Consignor>",
+    "<s_Notify_Country>",
+    "</s_Second_Notify_Country>",
+    "</s_Consignee_Country>",
+    "<s_Goods_Description>",
+    "</s_Consignor_Country>",
+    "</s_Consignee>",
+    "<s_Second_Notify_Country>",
+    "<s_Marks>",
+    "<s>",
+    "<s_Total_Weight>",
+    "</s_Notify>",
+    "</s_Goods_Description>",
+    "<s_Second_Notify>",
+    "<s_Total_Volume>",
+    "</s_Total_Weight>",
+    "</s>",
+    "<s_Consignee>",
+    "</s_Second_Notify>",
+    "</s_Total_Volume>",
+    "</s_Marks>",
+    "</s_Consignor>",
+    "</s_Total_Packages>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}