End of training

README.md

@@ -0,0 +1,96 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: microsoft/layoutlmv2-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- cord
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: layoutlmv2-finetuned-cord
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: cord
+      type: cord
+      config: cord
+      split: validation
+      args: cord
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9652945924132365
+    - name: Recall
+      type: recall
+      value: 0.9676375404530745
+    - name: F1
+      type: f1
+      value: 0.9664646464646465
+    - name: Accuracy
+      type: accuracy
+      value: 0.9702653247941445
+---
+
+<!-- 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. -->
+
+# layoutlmv2-finetuned-cord
+
+This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the cord dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2819
+- Precision: 0.9653
+- Recall: 0.9676
+- F1: 0.9665
+- Accuracy: 0.9703
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 400  | 1.2752          | 0.8527    | 0.8382 | 0.8454 | 0.8481   |
+| 1.9583        | 2.0   | 800  | 0.6372          | 0.8799    | 0.8948 | 0.8873 | 0.9021   |
+| 0.7097        | 3.0   | 1200 | 0.4255          | 0.9241    | 0.9264 | 0.9253 | 0.9414   |
+| 0.3845        | 4.0   | 1600 | 0.3021          | 0.9414    | 0.9482 | 0.9448 | 0.9611   |
+| 0.2699        | 5.0   | 2000 | 0.2819          | 0.9653    | 0.9676 | 0.9665 | 0.9703   |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,10 @@
+{
+    "test_accuracy": 0.9685507862303443,
+    "test_f1": 0.9523088569265707,
+    "test_loss": 0.28069764375686646,
+    "test_precision": 0.953030303030303,
+    "test_recall": 0.9515885022692889,
+    "test_runtime": 3.6555,
+    "test_samples_per_second": 27.356,
+    "test_steps_per_second": 3.556
+}

config.json

@@ -0,0 +1,196 @@
+{
+  "_name_or_path": "microsoft/layoutlmv2-base-uncased",
+  "architectures": [
+    "LayoutLMv2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "convert_sync_batchnorm": true,
+  "coordinate_size": 128,
+  "detectron2_config_args": {
+    "MODEL.ANCHOR_GENERATOR.SIZES": [
+      [
+        32
+      ],
+      [
+        64
+      ],
+      [
+        128
+      ],
+      [
+        256
+      ],
+      [
+        512
+      ]
+    ],
+    "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
+    "MODEL.FPN.IN_FEATURES": [
+      "res2",
+      "res3",
+      "res4",
+      "res5"
+    ],
+    "MODEL.MASK_ON": true,
+    "MODEL.PIXEL_STD": [
+      57.375,
+      57.12,
+      58.395
+    ],
+    "MODEL.POST_NMS_TOPK_TEST": 1000,
+    "MODEL.RESNETS.ASPECT_RATIOS": [
+      [
+        0.5,
+        1.0,
+        2.0
+      ]
+    ],
+    "MODEL.RESNETS.DEPTH": 101,
+    "MODEL.RESNETS.NUM_GROUPS": 32,
+    "MODEL.RESNETS.OUT_FEATURES": [
+      "res2",
+      "res3",
+      "res4",
+      "res5"
+    ],
+    "MODEL.RESNETS.SIZES": [
+      [
+        32
+      ],
+      [
+        64
+      ],
+      [
+        128
+      ],
+      [
+        256
+      ],
+      [
+        512
+      ]
+    ],
+    "MODEL.RESNETS.STRIDE_IN_1X1": false,
+    "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
+    "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
+    "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
+    "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
+    "MODEL.ROI_HEADS.IN_FEATURES": [
+      "p2",
+      "p3",
+      "p4",
+      "p5"
+    ],
+    "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
+    "MODEL.ROI_HEADS.NUM_CLASSES": 5,
+    "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
+    "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
+    "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
+    "MODEL.RPN.IN_FEATURES": [
+      "p2",
+      "p3",
+      "p4",
+      "p5",
+      "p6"
+    ],
+    "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
+    "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
+    "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
+  },
+  "fast_qkv": true,
+  "gradient_checkpointing": false,
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "has_visual_segment_embedding": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "I-menu.cnt",
+    "1": "I-menu.discountprice",
+    "2": "I-menu.etc",
+    "3": "I-menu.itemsubtotal",
+    "4": "I-menu.nm",
+    "5": "I-menu.num",
+    "6": "I-menu.price",
+    "7": "I-menu.sub_cnt",
+    "8": "I-menu.sub_etc",
+    "9": "I-menu.sub_nm",
+    "10": "I-menu.sub_price",
+    "11": "I-menu.sub_unitprice",
+    "12": "I-menu.unitprice",
+    "13": "I-menu.vatyn",
+    "14": "I-sub_total.discount_price",
+    "15": "I-sub_total.etc",
+    "16": "I-sub_total.othersvc_price",
+    "17": "I-sub_total.service_price",
+    "18": "I-sub_total.subtotal_price",
+    "19": "I-sub_total.tax_price",
+    "20": "I-total.cashprice",
+    "21": "I-total.changeprice",
+    "22": "I-total.creditcardprice",
+    "23": "I-total.emoneyprice",
+    "24": "I-total.menuqty_cnt",
+    "25": "I-total.menutype_cnt",
+    "26": "I-total.total_etc",
+    "27": "I-total.total_price",
+    "28": "I-void_menu.nm",
+    "29": "I-void_menu.price"
+  },
+  "image_feature_pool_shape": [
+    7,
+    7,
+    256
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I-menu.cnt": 0,
+    "I-menu.discountprice": 1,
+    "I-menu.etc": 2,
+    "I-menu.itemsubtotal": 3,
+    "I-menu.nm": 4,
+    "I-menu.num": 5,
+    "I-menu.price": 6,
+    "I-menu.sub_cnt": 7,
+    "I-menu.sub_etc": 8,
+    "I-menu.sub_nm": 9,
+    "I-menu.sub_price": 10,
+    "I-menu.sub_unitprice": 11,
+    "I-menu.unitprice": 12,
+    "I-menu.vatyn": 13,
+    "I-sub_total.discount_price": 14,
+    "I-sub_total.etc": 15,
+    "I-sub_total.othersvc_price": 16,
+    "I-sub_total.service_price": 17,
+    "I-sub_total.subtotal_price": 18,
+    "I-sub_total.tax_price": 19,
+    "I-total.cashprice": 20,
+    "I-total.changeprice": 21,
+    "I-total.creditcardprice": 22,
+    "I-total.emoneyprice": 23,
+    "I-total.menuqty_cnt": 24,
+    "I-total.menutype_cnt": 25,
+    "I-total.total_etc": 26,
+    "I-total.total_price": 27,
+    "I-void_menu.nm": 28,
+    "I-void_menu.price": 29
+  },
+  "layer_norm_eps": 1e-12,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 512,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "shape_size": 128,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192d9cd60dd6f4f0fac9ad930c28bb2f39f65f71959cb98d724c971f3b536fa3
+size 802136688

test_results.json

@@ -0,0 +1,10 @@
+{
+    "test_accuracy": 0.9685507862303443,
+    "test_f1": 0.9523088569265707,
+    "test_loss": 0.28069764375686646,
+    "test_precision": 0.953030303030303,
+    "test_recall": 0.9515885022692889,
+    "test_runtime": 3.6555,
+    "test_samples_per_second": 27.356,
+    "test_steps_per_second": 3.556
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be3bcd0f05c06b3ea3aedb9cc2dbe824ad498bbe6861cc2a6e9711dc0a50a18
+size 4728