Training in progress, step 500

README.md

@@ -0,0 +1,99 @@
+---
+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: 0.7467652495378928
+    - name: Recall
+      type: recall
+      value: 0.8027819175360159
+    - name: F1
+      type: f1
+      value: 0.7737610725401005
+    - name: Accuracy
+      type: accuracy
+      value: 0.8188517770117675
+---
+
+<!-- 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: 0.5984
+- Precision: 0.7468
+- Recall: 0.8028
+- F1: 0.7738
+- Accuracy: 0.8189
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.67  | 100  | 1.0197          | 0.5025    | 0.5981 | 0.5462 | 0.6622   |
+| No log        | 1.34  | 200  | 0.6833          | 0.6203    | 0.7238 | 0.6680 | 0.7608   |
+| No log        | 2.01  | 300  | 0.6237          | 0.6401    | 0.7794 | 0.7030 | 0.7846   |
+| No log        | 2.68  | 400  | 0.6028          | 0.6892    | 0.7392 | 0.7133 | 0.7771   |
+| 0.8343        | 3.36  | 500  | 0.5948          | 0.7175    | 0.7884 | 0.7512 | 0.7991   |
+| 0.8343        | 4.03  | 600  | 0.5953          | 0.7135    | 0.8028 | 0.7555 | 0.7961   |
+| 0.8343        | 4.7   | 700  | 0.5925          | 0.7354    | 0.7953 | 0.7642 | 0.8174   |
+| 0.8343        | 5.37  | 800  | 0.6055          | 0.7397    | 0.7933 | 0.7656 | 0.8134   |
+| 0.8343        | 6.04  | 900  | 0.5940          | 0.7535    | 0.8077 | 0.7797 | 0.8199   |
+| 0.3468        | 6.71  | 1000 | 0.5984          | 0.7468    | 0.8028 | 0.7738 | 0.8189   |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,68 @@
+{
+  "_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-ABN",
+    "2": "B-BILLER",
+    "3": "B-BILLER_ADDRESS",
+    "4": "B-BILLER_POST_CODE",
+    "5": "B-DUE_DATE",
+    "6": "B-GST",
+    "7": "B-INVOICE_DATE",
+    "8": "B-INVOICE_NUMBER",
+    "9": "B-SUBTOTAL",
+    "10": "B-TOTAL",
+    "11": "I-BILLER_ADDRESS"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ABN": 1,
+    "B-BILLER": 2,
+    "B-BILLER_ADDRESS": 3,
+    "B-BILLER_POST_CODE": 4,
+    "B-DUE_DATE": 5,
+    "B-GST": 6,
+    "B-INVOICE_DATE": 7,
+    "B-INVOICE_NUMBER": 8,
+    "B-SUBTOTAL": 9,
+    "B-TOTAL": 10,
+    "I-BILLER_ADDRESS": 11,
+    "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": "4.35.0.dev0",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
+  "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": ""
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f9a6460545edb1fbd48ff4dd83587c71211b84a3dc007d23b1f515b7bea38b
+size 503782186

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:ba1d3e10f06dcce028e49ac4cecd1142671a2caa391dfd9de37d544bfd3f9e4b
+size 4536