End of training

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: layoutmlv3_thursday_sep7_v5
+  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. -->
+
+# layoutmlv3_thursday_sep7_v5
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1416
+- Precision: 0.5517
+- Recall: 0.9412
+- F1: 0.6957
+- Accuracy: 0.9822
+
+## 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: 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        | 8.33  | 100  | 0.3243          | 0.5556    | 0.8824 | 0.6818 | 0.9485   |
+| No log        | 16.67 | 200  | 0.1584          | 0.6087    | 0.8235 | 0.7    | 0.9734   |
+| No log        | 25.0  | 300  | 0.1682          | 0.5517    | 0.9412 | 0.6957 | 0.9769   |
+| No log        | 33.33 | 400  | 0.1773          | 0.4545    | 0.8824 | 0.6    | 0.9734   |
+| 0.2633        | 41.67 | 500  | 0.1631          | 0.4375    | 0.8235 | 0.5714 | 0.9751   |
+| 0.2633        | 50.0  | 600  | 0.1526          | 0.5517    | 0.9412 | 0.6957 | 0.9769   |
+| 0.2633        | 58.33 | 700  | 0.1430          | 0.5517    | 0.9412 | 0.6957 | 0.9840   |
+| 0.2633        | 66.67 | 800  | 0.1497          | 0.5517    | 0.9412 | 0.6957 | 0.9822   |
+| 0.2633        | 75.0  | 900  | 0.1418          | 0.5517    | 0.9412 | 0.6957 | 0.9805   |
+| 0.0111        | 83.33 | 1000 | 0.1416          | 0.5517    | 0.9412 | 0.6957 | 0.9822   |
+
+
+### Framework versions
+
+- Transformers 4.34.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,70 @@
+{
+  "_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": "E-VALUE",
+    "1": "I-IGNORE",
+    "2": "S-KEY",
+    "3": "E-IGNORE",
+    "4": "S-IGNORE",
+    "5": "S-VALUE",
+    "6": "I-VALUE",
+    "7": "B-IGNORE",
+    "8": "B-VALUE",
+    "9": "B-TABLE",
+    "10": "O",
+    "11": "I-TABLE",
+    "12": "E-TABLE"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-IGNORE": 7,
+    "B-TABLE": 9,
+    "B-VALUE": 8,
+    "E-IGNORE": 3,
+    "E-TABLE": 12,
+    "E-VALUE": 0,
+    "I-IGNORE": 1,
+    "I-TABLE": 11,
+    "I-VALUE": 6,
+    "O": 10,
+    "S-IGNORE": 4,
+    "S-KEY": 2,
+    "S-VALUE": 5
+  },
+  "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": "4.34.0.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:f8baa4756b56a713a95ec5005c6e4c170cb8941043ef2ebce056eea87cba9e30
+size 503784749

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 +1,86 @@
+{
+  "add_prefix_space": true,
+  "apply_ocr": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "only_label_first_subword": true,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7aa71c78efdf5ae36c23a6d6be0d7e13205dc0f86a3f357d096f335aedc3b8a
+size 4027