layoutlmv3-finetuned-cordv2

README.md

@@ -0,0 +1,75 @@
+---
+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-cordv2
+  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-cordv2
+
+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: 0.1800
+- Precision: 0.9519
+- Recall: 0.9568
+- F1: 0.9544
+- Accuracy: 0.9656
+
+## 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: 2500
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.5625  | 250  | 0.7355          | 0.7503    | 0.7595 | 0.7549 | 0.8216   |
+| 1.0406        | 3.125   | 500  | 0.4019          | 0.8576    | 0.8787 | 0.8680 | 0.9006   |
+| 1.0406        | 4.6875  | 750  | 0.2671          | 0.9028    | 0.9260 | 0.9143 | 0.9384   |
+| 0.2814        | 6.25    | 1000 | 0.2293          | 0.9380    | 0.9332 | 0.9356 | 0.9473   |
+| 0.2814        | 7.8125  | 1250 | 0.1763          | 0.9426    | 0.9445 | 0.9435 | 0.9622   |
+| 0.1349        | 9.375   | 1500 | 0.1926          | 0.9437    | 0.9476 | 0.9456 | 0.9613   |
+| 0.1349        | 10.9375 | 1750 | 0.1848          | 0.9481    | 0.9579 | 0.9530 | 0.9647   |
+| 0.082         | 12.5    | 2000 | 0.2028          | 0.9490    | 0.9558 | 0.9524 | 0.9626   |
+| 0.082         | 14.0625 | 2250 | 0.1878          | 0.9510    | 0.9579 | 0.9544 | 0.9652   |
+| 0.0584        | 15.625  | 2500 | 0.1800          | 0.9519    | 0.9568 | 0.9544 | 0.9656   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,104 @@
+{
+  "_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": -100,
+    "1": 0,
+    "2": 1,
+    "3": 2,
+    "4": 3,
+    "5": 4,
+    "6": 5,
+    "7": 6,
+    "8": 7,
+    "9": 8,
+    "10": 9,
+    "11": 10,
+    "12": 11,
+    "13": 12,
+    "14": 13,
+    "15": 14,
+    "16": 15,
+    "17": 16,
+    "18": 17,
+    "19": 18,
+    "20": 19,
+    "21": 20,
+    "22": 21,
+    "23": 22,
+    "24": 23,
+    "25": 24,
+    "26": 25,
+    "27": 26,
+    "28": 27,
+    "29": 28
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "-100": 0,
+    "0": 1,
+    "1": 2,
+    "2": 3,
+    "3": 4,
+    "4": 5,
+    "5": 6,
+    "6": 7,
+    "7": 8,
+    "8": 9,
+    "9": 10,
+    "10": 11,
+    "11": 12,
+    "12": 13,
+    "13": 14,
+    "14": 15,
+    "15": 16,
+    "16": 17,
+    "17": 18,
+    "18": 19,
+    "19": 20,
+    "20": 21,
+    "21": 22,
+    "22": 23,
+    "23": 24,
+    "24": 25,
+    "25": 26,
+    "26": 27,
+    "27": 28,
+    "28": 29
+  },
+  "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": "4.41.2",
+  "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:d3f3cf279bdb22e6687c71ad17f7ba12651d3683c5868a7272f25e5530888d6a
+size 503788880

preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "apply_ocr",
+    "ocr_lang",
+    "tesseract_config",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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/Jul11_19-14-55_f356370f76c2/events.out.tfevents.1720725322.f356370f76c2.333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fb638dd33714b5ca4316282d6d00913ce224697eec4ceecfe921c5487634a7
+size 12144

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 sha256:1129bbf59fbcee9f619176009cfbedf704a346eb1c51d8dbffff4aca49c938db
+size 5112