Training in progress, step 500

README.md

@@ -0,0 +1,67 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: microsoft/layoutlmv3-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: layoutlmv3-finetuned-cord_200
+  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. -->
+
+# layoutlmv3-finetuned-cord_200
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2000
+- Precision: 0.9557
+- Recall: 0.9713
+- F1: 0.9634
+- Accuracy: 0.9648
+
+## 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: 1e-05
+- train_batch_size: 5
+- eval_batch_size: 5
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 200
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.625 | 100  | 0.2075          | 0.9483    | 0.9689 | 0.9585 | 0.9618   |
+| No log        | 1.25  | 200  | 0.2000          | 0.9557    | 0.9713 | 0.9634 | 0.9648   |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,122 @@
+{
+  "_name_or_path": "microsoft/layoutlmv3-base",
+  "architectures": [
+    "LayoutLMv3ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 128,
+  "eos_token_id": 2,
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-MENU.CNT",
+    "2": "B-MENU.DISCOUNTPRICE",
+    "3": "B-MENU.NM",
+    "4": "B-MENU.NUM",
+    "5": "B-MENU.PRICE",
+    "6": "B-MENU.SUB.CNT",
+    "7": "B-MENU.SUB.NM",
+    "8": "B-MENU.SUB.PRICE",
+    "9": "B-MENU.UNITPRICE",
+    "10": "B-SUB_TOTAL.DISCOUNT_PRICE",
+    "11": "B-SUB_TOTAL.ETC",
+    "12": "B-SUB_TOTAL.SERVICE_PRICE",
+    "13": "B-SUB_TOTAL.SUBTOTAL_PRICE",
+    "14": "B-SUB_TOTAL.TAX_PRICE",
+    "15": "B-TOTAL.CASHPRICE",
+    "16": "B-TOTAL.CHANGEPRICE",
+    "17": "B-TOTAL.CREDITCARDPRICE",
+    "18": "B-TOTAL.MENUQTY_CNT",
+    "19": "B-TOTAL.TOTAL_PRICE",
+    "20": "I-MENU.CNT",
+    "21": "I-MENU.DISCOUNTPRICE",
+    "22": "I-MENU.NM",
+    "23": "I-MENU.NUM",
+    "24": "I-MENU.PRICE",
+    "25": "I-MENU.SUB.CNT",
+    "26": "I-MENU.SUB.NM",
+    "27": "I-MENU.SUB.PRICE",
+    "28": "I-MENU.UNITPRICE",
+    "29": "I-SUB_TOTAL.DISCOUNT_PRICE",
+    "30": "I-SUB_TOTAL.ETC",
+    "31": "I-SUB_TOTAL.SERVICE_PRICE",
+    "32": "I-SUB_TOTAL.SUBTOTAL_PRICE",
+    "33": "I-SUB_TOTAL.TAX_PRICE",
+    "34": "I-TOTAL.CASHPRICE",
+    "35": "I-TOTAL.CHANGEPRICE",
+    "36": "I-TOTAL.CREDITCARDPRICE",
+    "37": "I-TOTAL.MENUQTY_CNT",
+    "38": "I-TOTAL.TOTAL_PRICE"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-MENU.CNT": 1,
+    "B-MENU.DISCOUNTPRICE": 2,
+    "B-MENU.NM": 3,
+    "B-MENU.NUM": 4,
+    "B-MENU.PRICE": 5,
+    "B-MENU.SUB.CNT": 6,
+    "B-MENU.SUB.NM": 7,
+    "B-MENU.SUB.PRICE": 8,
+    "B-MENU.UNITPRICE": 9,
+    "B-SUB_TOTAL.DISCOUNT_PRICE": 10,
+    "B-SUB_TOTAL.ETC": 11,
+    "B-SUB_TOTAL.SERVICE_PRICE": 12,
+    "B-SUB_TOTAL.SUBTOTAL_PRICE": 13,
+    "B-SUB_TOTAL.TAX_PRICE": 14,
+    "B-TOTAL.CASHPRICE": 15,
+    "B-TOTAL.CHANGEPRICE": 16,
+    "B-TOTAL.CREDITCARDPRICE": 17,
+    "B-TOTAL.MENUQTY_CNT": 18,
+    "B-TOTAL.TOTAL_PRICE": 19,
+    "I-MENU.CNT": 20,
+    "I-MENU.DISCOUNTPRICE": 21,
+    "I-MENU.NM": 22,
+    "I-MENU.NUM": 23,
+    "I-MENU.PRICE": 24,
+    "I-MENU.SUB.CNT": 25,
+    "I-MENU.SUB.NM": 26,
+    "I-MENU.SUB.PRICE": 27,
+    "I-MENU.UNITPRICE": 28,
+    "I-SUB_TOTAL.DISCOUNT_PRICE": 29,
+    "I-SUB_TOTAL.ETC": 30,
+    "I-SUB_TOTAL.SERVICE_PRICE": 31,
+    "I-SUB_TOTAL.SUBTOTAL_PRICE": 32,
+    "I-SUB_TOTAL.TAX_PRICE": 33,
+    "I-TOTAL.CASHPRICE": 34,
+    "I-TOTAL.CHANGEPRICE": 35,
+    "I-TOTAL.CREDITCARDPRICE": 36,
+    "I-TOTAL.MENUQTY_CNT": 37,
+    "I-TOTAL.TOTAL_PRICE": 38,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv3",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "patch_size": 16,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "second_input_size": 112,
+  "shape_size": 128,
+  "text_embed": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6148f3560d6afb9bd8d81c000739ce25a4652830557ff34356ccae02223b24
+size 503816564

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
+}

runs/Aug25_23-01-46_50648b3d681e/events.out.tfevents.1724626911.50648b3d681e.3875.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e928b649106176059bed576c3e0229c03bd566b1450f5ee584f31487130663
+size 15676

runs/Aug25_23-01-46_50648b3d681e/events.out.tfevents.1724627987.50648b3d681e.3875.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7e9b82b2cdcf1843b2cfb1b7339dffe9896ae390c32662274356cc88b75fbd
+size 16213

runs/Aug25_23-45-36_50648b3d681e/events.out.tfevents.1724629544.50648b3d681e.3875.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e23c85730ea0f32c605caf4f69c6e161979115997b475fb2bb9740522924080
+size 8971

runs/Aug26_00-09-31_50648b3d681e/events.out.tfevents.1724630978.50648b3d681e.3875.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fdef55514b8a10c0df36a4e7956039d2a9e4aba9814b1f29e69f969f6309122
+size 8830

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,79 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "apply_ocr": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "only_label_first_subword": true,
+  "pad_token": "<pad>",
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": "</s>",
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa80865bc3db316942319c6834181cafc5e27a5146c322b4cab132f2275d2669
+size 5240