End of training

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: donut-base-Label-studio-707-invoices
+  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-Label-studio-707-invoices
+
+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: 12
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- Pytorch 1.12.1+cu113
+- Datasets 2.6.1
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,83 @@
+{
+  "</s_BUY_ADD>": 57578,
+  "</s_BUY_PAN_ID>": 57600,
+  "</s_BUY_PAN_NO>": 57598,
+  "</s_CGST_ID>": 57576,
+  "</s_CGST_RATE>": 57574,
+  "</s_CGST_VALUE>": 57572,
+  "</s_CIN_ID>": 57596,
+  "</s_CIN_NO>": 57594,
+  "</s_CUSTOMER_NAME>": 57570,
+  "</s_CUSTOMER_PO_ID>": 57586,
+  "</s_CUSTOMER_PO_NO>": 57584,
+  "</s_GSTIN_ID>": 57568,
+  "</s_GSTIN_NO>": 57566,
+  "</s_GSTIN_SELL_ID>": 57564,
+  "</s_GSTIN_SELL_NO>": 57562,
+  "</s_IGST_ID>": 57592,
+  "</s_IGST_RATE>": 57560,
+  "</s_IGST_VALUE>": 57558,
+  "</s_INVOICE_DATE_ID>": 57556,
+  "</s_INVOICE_DATE_NO>": 57554,
+  "</s_INVOICE_ID>": 57552,
+  "</s_INVOICE_NO>": 57550,
+  "</s_MODE_OF_PAY_ID>": 57548,
+  "</s_MODE_OF_PAY_NO>": 57546,
+  "</s_REVERSE_CHARGE_ID>": 57588,
+  "</s_REVERSE_CHARGE_NO>": 57602,
+  "</s_SELL_ADD>": 57544,
+  "</s_SELL_PAN_ID>": 57582,
+  "</s_SELL_PAN_NO>": 57580,
+  "</s_SGST_ID>": 57542,
+  "</s_SGST_RATE>": 57540,
+  "</s_SGST_VALUE>": 57538,
+  "</s_SUBTOTAL_ID>": 57536,
+  "</s_SUBTOTAL_VALUE>": 57534,
+  "</s_TOTAL_ID>": 57532,
+  "</s_TOTAL_NO>": 57530,
+  "</s_VEHICLE_ID>": 57590,
+  "</s_VEHICLE_NO>": 57528,
+  "</s_VENDER_NAME>": 57526,
+  "<s_BUY_ADD>": 57577,
+  "<s_BUY_PAN_ID>": 57599,
+  "<s_BUY_PAN_NO>": 57597,
+  "<s_CGST_ID>": 57575,
+  "<s_CGST_RATE>": 57573,
+  "<s_CGST_VALUE>": 57571,
+  "<s_CIN_ID>": 57595,
+  "<s_CIN_NO>": 57593,
+  "<s_CUSTOMER_NAME>": 57569,
+  "<s_CUSTOMER_PO_ID>": 57585,
+  "<s_CUSTOMER_PO_NO>": 57583,
+  "<s_GSTIN_ID>": 57567,
+  "<s_GSTIN_NO>": 57565,
+  "<s_GSTIN_SELL_ID>": 57563,
+  "<s_GSTIN_SELL_NO>": 57561,
+  "<s_IGST_ID>": 57591,
+  "<s_IGST_RATE>": 57559,
+  "<s_IGST_VALUE>": 57557,
+  "<s_INVOICE_DATE_ID>": 57555,
+  "<s_INVOICE_DATE_NO>": 57553,
+  "<s_INVOICE_ID>": 57551,
+  "<s_INVOICE_NO>": 57549,
+  "<s_MODE_OF_PAY_ID>": 57547,
+  "<s_MODE_OF_PAY_NO>": 57545,
+  "<s_REVERSE_CHARGE_ID>": 57587,
+  "<s_REVERSE_CHARGE_NO>": 57601,
+  "<s_SELL_ADD>": 57543,
+  "<s_SELL_PAN_ID>": 57581,
+  "<s_SELL_PAN_NO>": 57579,
+  "<s_SGST_ID>": 57541,
+  "<s_SGST_RATE>": 57539,
+  "<s_SGST_VALUE>": 57537,
+  "<s_SUBTOTAL_ID>": 57535,
+  "<s_SUBTOTAL_VALUE>": 57533,
+  "<s_TOTAL_ID>": 57531,
+  "<s_TOTAL_NO>": 57529,
+  "<s_VEHICLE_ID>": 57589,
+  "<s_VEHICLE_NO>": 57527,
+  "<s_VENDER_NAME>": 57525,
+  "<s_iitcdip>": 57523,
+  "<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": [
+    720,
+    960
+  ]
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812d3a6afe383fdf8214243fbfbb7a7387643257c9f080bb1b730ee73f06b901
+oid sha256:56e1203437933812a010544342615348379290fee68439f385444381098a1f9b
 size 809494907

runs/Nov08_10-06-57_8b5226e045a6/events.out.tfevents.1667902029.8b5226e045a6.77.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c57e52533bf963269e7437afc515709bcf5951981e0f9e3ad00fa06e3d0a51
-size 17034
+oid sha256:4a21e29d1241b948898be6257fd88198b23e69cda11ed26ba92c95936838df68
+size 23511

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 +1,97 @@
+{
+  "additional_special_tokens": [
+    "<s_VENDER_NAME>",
+    "</s_VENDER_NAME>",
+    "<s_VEHICLE_NO>",
+    "</s_VEHICLE_NO>",
+    "<s_VEHICLE_ID>",
+    "</s_VEHICLE_ID>",
+    "<s_TOTAL_NO>",
+    "</s_TOTAL_NO>",
+    "<s_TOTAL_ID>",
+    "</s_TOTAL_ID>",
+    "<s_SUBTOTAL_VALUE>",
+    "</s_SUBTOTAL_VALUE>",
+    "<s_SUBTOTAL_ID>",
+    "</s_SUBTOTAL_ID>",
+    "<s_SGST_VALUE>",
+    "</s_SGST_VALUE>",
+    "<s_SGST_RATE>",
+    "</s_SGST_RATE>",
+    "<s_SGST_ID>",
+    "</s_SGST_ID>",
+    "<s_SELL_PAN_NO>",
+    "</s_SELL_PAN_NO>",
+    "<s_SELL_PAN_ID>",
+    "</s_SELL_PAN_ID>",
+    "<s_SELL_ADD>",
+    "</s_SELL_ADD>",
+    "<s_REVERSE_CHARGE_NO>",
+    "</s_REVERSE_CHARGE_NO>",
+    "<s_REVERSE_CHARGE_ID>",
+    "</s_REVERSE_CHARGE_ID>",
+    "<s_INVOICE_NO>",
+    "</s_INVOICE_NO>",
+    "<s_INVOICE_ID>",
+    "</s_INVOICE_ID>",
+    "<s_INVOICE_DATE_NO>",
+    "</s_INVOICE_DATE_NO>",
+    "<s_INVOICE_DATE_ID>",
+    "</s_INVOICE_DATE_ID>",
+    "<s_GSTIN_SELL_NO>",
+    "</s_GSTIN_SELL_NO>",
+    "<s_GSTIN_SELL_ID>",
+    "</s_GSTIN_SELL_ID>",
+    "<s_GSTIN_NO>",
+    "</s_GSTIN_NO>",
+    "<s_GSTIN_ID>",
+    "</s_GSTIN_ID>",
+    "<s_CUSTOMER_PO_ID>",
+    "</s_CUSTOMER_PO_ID>",
+    "<s_CUSTOMER_NAME>",
+    "</s_CUSTOMER_NAME>",
+    "<s_CIN_NO>",
+    "</s_CIN_NO>",
+    "<s_CIN_ID>",
+    "</s_CIN_ID>",
+    "<s_CGST_VALUE>",
+    "</s_CGST_VALUE>",
+    "<s_CGST_RATE>",
+    "</s_CGST_RATE>",
+    "<s_CGST_ID>",
+    "</s_CGST_ID>",
+    "<s_BUY_ADD>",
+    "</s_BUY_ADD>",
+    "<s_IGST_VALUE>",
+    "</s_IGST_VALUE>",
+    "<s_IGST_ID>",
+    "</s_IGST_ID>",
+    "<s_BUY_PAN_NO>",
+    "</s_BUY_PAN_NO>",
+    "<s_BUY_PAN_ID>",
+    "</s_BUY_PAN_ID>",
+    "<s_IGST_RATE>",
+    "</s_IGST_RATE>",
+    "<s_MODE_OF_PAY_ID>",
+    "</s_MODE_OF_PAY_ID>",
+    "<s_CUSTOMER_PO_NO>",
+    "</s_CUSTOMER_PO_NO>",
+    "<s_MODE_OF_PAY_NO>",
+    "</s_MODE_OF_PAY_NO>",
+    "<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": "Prem11100/donut-base-Label-studio",
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}