End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: dof-passport-1
+  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. -->
+
+# dof-passport-1
+
+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: 3e-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: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- Pytorch 1.12.1+cu113
+- Datasets 2.7.0
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</s_country_code>": 57542,
+  "</s_date_of_birth>": 57540,
+  "</s_date_of_expiry>": 57538,
+  "</s_date_of_issue>": 57536,
+  "</s_given_name>": 57534,
+  "</s_nationality>": 57532,
+  "</s_passport_no>": 57530,
+  "</s_place_of_birth>": 57528,
+  "</s_place_of_issue>": 57526,
+  "</s_sex>": 57548,
+  "</s_surname>": 57546,
+  "</s_type>": 57544,
+  "<s_country_code>": 57541,
+  "<s_date_of_birth>": 57539,
+  "<s_date_of_expiry>": 57537,
+  "<s_date_of_issue>": 57535,
+  "<s_given_name>": 57533,
+  "<s_iitcdip>": 57523,
+  "<s_nationality>": 57531,
+  "<s_passport_no>": 57529,
+  "<s_place_of_birth>": 57527,
+  "<s_place_of_issue>": 57525,
+  "<s_sex>": 57547,
+  "<s_surname>": 57545,
+  "<s_synthdog>": 57524,
+  "<s_type>": 57543,
+  "<sep/>": 57522
+}

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "feature_extractor_type": "DonutFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "size": [
+    960,
+    1280
+  ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c397bf60eb5acb615bec1b57309cd312020c388bbdcb395654ca16b5151802d
+oid sha256:ded5a7f7f86cb63b96fd6a298655745d0c8487de2e85a4776558992c1074ad27
 size 809273723

runs/Nov17_08-24-46_f208b1123d20/events.out.tfevents.1668673503.f208b1123d20.79.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32475f674bdae5dd417af586f31ed40a04b6c768878e03408e802a3e7d45f75f
-size 8206
+oid sha256:175198bc44378c05e0ce7299cba966ae40cbc6506474a1bf1ca24829efe08057
+size 12639

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 +1,43 @@
+{
+  "additional_special_tokens": [
+    "<s_place_of_issue>",
+    "</s_place_of_issue>",
+    "<s_place_of_birth>",
+    "</s_place_of_birth>",
+    "<s_passport_no>",
+    "</s_passport_no>",
+    "<s_nationality>",
+    "</s_nationality>",
+    "<s_given_name>",
+    "</s_given_name>",
+    "<s_date_of_issue>",
+    "</s_date_of_issue>",
+    "<s_date_of_expiry>",
+    "</s_date_of_expiry>",
+    "<s_date_of_birth>",
+    "</s_date_of_birth>",
+    "<s_country_code>",
+    "</s_country_code>",
+    "<s_type>",
+    "</s_type>",
+    "<s_surname>",
+    "</s_surname>",
+    "<s_sex>",
+    "</s_sex>",
+    "<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>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "naver-clova-ix/donut-base",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}