End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: dof-invoice-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-invoice-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: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- Pytorch 1.13.0
+- Datasets 2.6.1
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,27 @@
+{
+  "</s_due_date>": 57540,
+  "</s_invoice_date>": 57538,
+  "</s_invoice_id>": 57536,
+  "</s_payment_terms>": 57546,
+  "</s_receiver_address>": 57534,
+  "</s_receiver_name>": 57532,
+  "</s_sub_total>": 57542,
+  "</s_supplier_address>": 57530,
+  "</s_supplier_name>": 57528,
+  "</s_tax_amount>": 57544,
+  "</s_total>": 57526,
+  "<s_due_date>": 57539,
+  "<s_iitcdip>": 57523,
+  "<s_invoice_date>": 57537,
+  "<s_invoice_id>": 57535,
+  "<s_payment_terms>": 57545,
+  "<s_receiver_address>": 57533,
+  "<s_receiver_name>": 57531,
+  "<s_sub_total>": 57541,
+  "<s_supplier_address>": 57529,
+  "<s_supplier_name>": 57527,
+  "<s_synthdog>": 57524,
+  "<s_tax_amount>": 57543,
+  "<s_total>": 57525,
+  "<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:b8b085ac2c4c76176feb89becde020af2b894b257ab3c3e1c56b14ebb5760ee3
+oid sha256:e5a69cf3bc64ad976479a5639d5b1a24eb0a170d35ba420a4d879d93562d036a
 size 809269017

runs/Nov15_06-38-07_instance-gp-s/events.out.tfevents.1668494316.instance-gp-s.3147.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3fdde1bd25b2e39548f0e1b4b64e9580d70b766b1afc03fc0c183fca8574593
-size 8828
+oid sha256:f376adc7b8a39d1c80ddd069b603f43eb12568b434fffa9088b779a58376fcf9
+size 22527

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_total>",
+    "</s_total>",
+    "<s_supplier_name>",
+    "</s_supplier_name>",
+    "<s_supplier_address>",
+    "</s_supplier_address>",
+    "<s_receiver_name>",
+    "</s_receiver_name>",
+    "<s_receiver_address>",
+    "</s_receiver_address>",
+    "<s_invoice_id>",
+    "</s_invoice_id>",
+    "<s_invoice_date>",
+    "</s_invoice_date>",
+    "<s_due_date>",
+    "</s_due_date>",
+    "<s_sub_total>",
+    "</s_sub_total>",
+    "<s_tax_amount>",
+    "</s_tax_amount>",
+    "<s_payment_terms>",
+    "</s_payment_terms>",
+    "<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>"
+}