End of training

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: donut-id-model-525-v1.0
+  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-id-model-525-v1.0
+
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on an unknown 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: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 6
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.23.1
+- Pytorch 1.12.1+cu113
+- Datasets 2.7.1
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,45 @@
+{
+  "</s_address_1>": 57548,
+  "</s_address_2>": 57546,
+  "</s_cc_no>": 57562,
+  "</s_country>": 57544,
+  "</s_dob>": 57542,
+  "</s_doc_type>": 57540,
+  "</s_doe>": 57538,
+  "</s_doi>": 57536,
+  "</s_fname>": 57534,
+  "</s_gender>": 57560,
+  "</s_id_no>": 57558,
+  "</s_license_no>": 57532,
+  "</s_lname>": 57530,
+  "</s_mname>": 57528,
+  "</s_mrz_line0>": 57564,
+  "</s_mrz_line1>": 57552,
+  "</s_mrz_line2>": 57550,
+  "</s_name>": 57556,
+  "</s_pob>": 57526,
+  "</s_race>": 57554,
+  "<s_address_1>": 57547,
+  "<s_address_2>": 57545,
+  "<s_cc_no>": 57561,
+  "<s_country>": 57543,
+  "<s_dob>": 57541,
+  "<s_doc_type>": 57539,
+  "<s_doe>": 57537,
+  "<s_doi>": 57535,
+  "<s_fname>": 57533,
+  "<s_gender>": 57559,
+  "<s_id_no>": 57557,
+  "<s_iitcdip>": 57523,
+  "<s_license_no>": 57531,
+  "<s_lname>": 57529,
+  "<s_mname>": 57527,
+  "<s_mrz_line0>": 57563,
+  "<s_mrz_line1>": 57551,
+  "<s_mrz_line2>": 57549,
+  "<s_name>": 57555,
+  "<s_pob>": 57525,
+  "<s_race>": 57553,
+  "<s_synthdog>": 57524,
+  "<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": [
+    525,
+    525
+  ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b186ccfcc5d158cde4433a8a05c4e1bf1200186051ab504536e643f59da29c3c
+oid sha256:f535bce124a2b461623a4707e0e342fd1c0ceedc10466bf0524402706f3c6075
 size 809339259

runs/Dec07_05-54-14_289cca4a4952/events.out.tfevents.1670392462.289cca4a4952.114.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94caa3c8932e38ef18e4a64b8804f6e545536e0cdec1d5b585b0757128d5d823
-size 13421
+oid sha256:bfae221f00d1373207cf5fb7d25a6bb1aabaf464f795e9a7cb985e894635fdcd
+size 39951

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 +1,59 @@
+{
+  "additional_special_tokens": [
+    "<s_pob>",
+    "</s_pob>",
+    "<s_mname>",
+    "</s_mname>",
+    "<s_lname>",
+    "</s_lname>",
+    "<s_license_no>",
+    "</s_license_no>",
+    "<s_fname>",
+    "</s_fname>",
+    "<s_doi>",
+    "</s_doi>",
+    "<s_doe>",
+    "</s_doe>",
+    "<s_doc_type>",
+    "</s_doc_type>",
+    "<s_dob>",
+    "</s_dob>",
+    "<s_country>",
+    "</s_country>",
+    "<s_address_2>",
+    "</s_address_2>",
+    "<s_address_1>",
+    "</s_address_1>",
+    "<s_mrz_line2>",
+    "</s_mrz_line2>",
+    "<s_mrz_line1>",
+    "</s_mrz_line1>",
+    "<s_race>",
+    "</s_race>",
+    "<s_name>",
+    "</s_name>",
+    "<s_id_no>",
+    "</s_id_no>",
+    "<s_gender>",
+    "</s_gender>",
+    "<s_cc_no>",
+    "</s_cc_no>",
+    "<s_mrz_line0>",
+    "</s_mrz_line0>",
+    "<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>"
+}