End of training

README.md

@@ -0,0 +1,99 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: microsoft/layoutlmv3-base
+tags:
+- generated_from_trainer
+datasets:
+- format_dataset
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: format_dataset
+      type: format_dataset
+      config: assesment dataset
+      split: test
+      args: assesment dataset
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8869778869778869
+    - name: Recall
+      type: recall
+      value: 0.9025
+    - name: F1
+      type: f1
+      value: 0.8946716232961586
+    - name: Accuracy
+      type: accuracy
+      value: 0.9977016777752241
+---
+
+<!-- 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 format_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0089
+- Precision: 0.8870
+- Recall: 0.9025
+- F1: 0.8947
+- Accuracy: 0.9977
+
+## 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        | 0.62  | 100  | 0.0405          | 0.0       | 0.0    | 0.0    | 0.9877   |
+| No log        | 1.25  | 200  | 0.0170          | 0.7538    | 0.735  | 0.7443 | 0.9949   |
+| No log        | 1.88  | 300  | 0.0131          | 0.7261    | 0.875  | 0.7937 | 0.9956   |
+| No log        | 2.5   | 400  | 0.0123          | 0.7692    | 0.85   | 0.8076 | 0.9959   |
+| 0.0271        | 3.12  | 500  | 0.0105          | 0.8098    | 0.905  | 0.8548 | 0.9968   |
+| 0.0271        | 3.75  | 600  | 0.0106          | 0.8460    | 0.8925 | 0.8686 | 0.9972   |
+| 0.0271        | 4.38  | 700  | 0.0086          | 0.8504    | 0.895  | 0.8721 | 0.9973   |
+| 0.0271        | 5.0   | 800  | 0.0109          | 0.8871    | 0.845  | 0.8656 | 0.9972   |
+| 0.0271        | 5.62  | 900  | 0.0085          | 0.8883    | 0.895  | 0.8917 | 0.9977   |
+| 0.0042        | 6.25  | 1000 | 0.0089          | 0.8870    | 0.9025 | 0.8947 | 0.9977   |
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,50 @@
+{
+  "_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": "Ignore",
+    "1": "B-total_amount",
+    "2": "I-total_amount"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-total_amount": 1,
+    "I-total_amount": 2,
+    "Ignore": 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": "4.38.0.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:accd8861d454dfc06e145363af2b130bf479658238ba344f8a318772b29328cb
+size 501343228

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/Feb05_15-00-56_b6fc4add67b8/events.out.tfevents.1707145257.b6fc4add67b8.155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5373991dcbadcd740582f08a0b2bf66df5b7f783afc07973fae191795aeb78e
+size 9836

runs/Feb05_15-04-39_b6fc4add67b8/events.out.tfevents.1707145492.b6fc4add67b8.155.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1365f3f659b59d70d27b6b2f744c0220f62ad4d4c7ec48eb3da6cc56f8913285
+size 10241

runs/Feb05_15-04-39_b6fc4add67b8/events.out.tfevents.1707146302.b6fc4add67b8.155.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263acabad134934316f4c665aa389d75a18be5490086315cb7663b9137de1d2b
+size 560

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 sha256:1b2ee25049c474919c325e26368577ee3a41d4987e6e8e5f2ed11db55b0db0ba
+size 4728