adamadam111/layoutlmv3b-finetuned-funsd-01

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:
+- funsd
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: layoutlmv3-finetuned-funsd
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: funsd
+      type: funsd
+      config: funsd
+      split: test
+      args: funsd
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.7822618488972314
+    - name: Recall
+      type: recall
+      value: 0.8281172379533035
+    - name: F1
+      type: f1
+      value: 0.8045366795366795
+    - name: Accuracy
+      type: accuracy
+      value: 0.8135029121597528
+---
+
+<!-- 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-funsd
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the funsd dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1059
+- Precision: 0.7823
+- Recall: 0.8281
+- F1: 0.8045
+- Accuracy: 0.8135
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.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        | 10.0  | 100  | 0.7158          | 0.6964    | 0.7690 | 0.7309 | 0.7833   |
+| No log        | 20.0  | 200  | 0.7508          | 0.7420    | 0.8058 | 0.7726 | 0.8076   |
+| No log        | 30.0  | 300  | 0.8085          | 0.7678    | 0.8097 | 0.7882 | 0.8078   |
+| No log        | 40.0  | 400  | 0.9083          | 0.7689    | 0.8147 | 0.7911 | 0.8061   |
+| 0.3419        | 50.0  | 500  | 0.9294          | 0.7840    | 0.8296 | 0.8062 | 0.8128   |
+| 0.3419        | 60.0  | 600  | 1.0036          | 0.7807    | 0.8366 | 0.8077 | 0.8178   |
+| 0.3419        | 70.0  | 700  | 1.0983          | 0.7727    | 0.8241 | 0.7976 | 0.8044   |
+| 0.3419        | 80.0  | 800  | 1.1092          | 0.7921    | 0.8251 | 0.8083 | 0.8064   |
+| 0.3419        | 90.0  | 900  | 1.1010          | 0.7780    | 0.8306 | 0.8035 | 0.8133   |
+| 0.0261        | 100.0 | 1000 | 1.1059          | 0.7823    | 0.8281 | 0.8045 | 0.8135   |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,57 @@
+{
+  "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-HEADER",
+    "2": "I-HEADER",
+    "3": "B-QUESTION",
+    "4": "I-QUESTION",
+    "5": "B-ANSWER",
+    "6": "I-ANSWER"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANSWER": 5,
+    "B-HEADER": 1,
+    "B-QUESTION": 3,
+    "I-ANSWER": 6,
+    "I-HEADER": 2,
+    "I-QUESTION": 4,
+    "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": "4.51.3",
+  "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 sha256:3829d4b08b87dd70e8d3ab3f0ce8e401a5b3ab3684c2d72669b70449d0eae698
+size 501355532

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/Apr24_14-02-59_e72df302eee4/events.out.tfevents.1745503383.e72df302eee4.198.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ab30e17c5c90eb4153629aa4ea06638d5c38f759a056555844cd129203cd99
+size 7497

runs/Apr24_14-20-44_e72df302eee4/events.out.tfevents.1745504445.e72df302eee4.198.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923ab5b4310f1bbde118a90b1237b176d9c9356e4e68f39f183c334787d0c2f1
+size 9594

runs/Apr24_14-43-34_e72df302eee4/events.out.tfevents.1745505815.e72df302eee4.198.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2d620fb1e932dccea54e8857054537b50dc70ec233857b3b896eba2d9c1431
+size 11103

runs/Apr24_15-03-39_e72df302eee4/events.out.tfevents.1745507020.e72df302eee4.198.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6678e6b82845e4660a9cf383aaf386a4e1e01d0d3814d5a2f0cf25b5dfa77eb4
+size 11105

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:e61d8c0301d5f6d8aa9846c3b3b6b6d81cb76cd12681008ced4dd4d7e42a2b19
+size 5368