End of training

README.md

@@ -0,0 +1,100 @@
+---
+library_name: transformers
+license: cc-by-nc-sa-4.0
+base_model: microsoft/layoutlmv3-base
+tags:
+- generated_from_trainer
+datasets:
+- layoutlmv3
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: layoutlmv3
+      type: layoutlmv3
+      config: InvoiceExtraction
+      split: test
+      args: InvoiceExtraction
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8860759493670886
+    - name: Recall
+      type: recall
+      value: 0.9210526315789473
+    - name: F1
+      type: f1
+      value: 0.9032258064516129
+    - name: Accuracy
+      type: accuracy
+      value: 0.94375
+---
+
+<!-- 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. -->
+
+# test
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the layoutlmv3 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3028
+- Precision: 0.8861
+- Recall: 0.9211
+- F1: 0.9032
+- Accuracy: 0.9437
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 4.3478  | 100  | 0.6867          | 0.6842    | 0.6842 | 0.6842 | 0.8063   |
+| No log        | 8.6957  | 200  | 0.2381          | 0.8625    | 0.9079 | 0.8846 | 0.9313   |
+| No log        | 13.0435 | 300  | 0.2598          | 0.8846    | 0.9079 | 0.8961 | 0.9313   |
+| No log        | 17.3913 | 400  | 0.2165          | 0.8625    | 0.9079 | 0.8846 | 0.9375   |
+| 0.3281        | 21.7391 | 500  | 0.2037          | 0.8625    | 0.9079 | 0.8846 | 0.9375   |
+| 0.3281        | 26.0870 | 600  | 0.2571          | 0.8861    | 0.9211 | 0.9032 | 0.9437   |
+| 0.3281        | 30.4348 | 700  | 0.2735          | 0.8861    | 0.9211 | 0.9032 | 0.9437   |
+| 0.3281        | 34.7826 | 800  | 0.2993          | 0.8861    | 0.9211 | 0.9032 | 0.9437   |
+| 0.3281        | 39.1304 | 900  | 0.3044          | 0.8861    | 0.9211 | 0.9032 | 0.9437   |
+| 0.012         | 43.4783 | 1000 | 0.3028          | 0.8861    | 0.9211 | 0.9032 | 0.9437   |
+
+
+### Framework versions
+
+- Transformers 4.47.0.dev0
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,64 @@
+{
+  "_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": "line_product_order",
+    "1": "invoice_number",
+    "2": "vendor_number",
+    "3": "invoice_date",
+    "4": "due_date",
+    "5": "total_amount",
+    "6": "line_product_configuration",
+    "7": "line_quantity",
+    "8": "line_price",
+    "9": "line_total_amount"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "due_date": 4,
+    "invoice_date": 3,
+    "invoice_number": 1,
+    "line_price": 8,
+    "line_product_configuration": 6,
+    "line_product_order": 0,
+    "line_quantity": 7,
+    "line_total_amount": 9,
+    "total_amount": 5,
+    "vendor_number": 2
+  },
+  "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": "4.47.0.dev0",
+  "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 sha256:352e62fbedf08281fccd7e6f0f2f47964c2b9bfbb8b6351f1f96681a09bf94df
+size 503727360

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": ""
+}

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 +1,80 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "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 sha256:0e3d9308785243089d2c6abd5e574d7af7989f889c57e13d4adf4d909b677593
+size 5304