End of training

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+base_model: microsoft/layoutlm-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- funsd
+model-index:
+- name: layoutlm-funsd-c
+  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. -->
+
+# layoutlm-funsd-c
+
+This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7152
+- Answer: {'precision': 0.7134894091415831, 'recall': 0.7911001236093943, 'f1': 0.7502930832356389, 'number': 809}
+- Header: {'precision': 0.31007751937984496, 'recall': 0.33613445378151263, 'f1': 0.3225806451612903, 'number': 119}
+- Question: {'precision': 0.7805309734513274, 'recall': 0.828169014084507, 'f1': 0.8036446469248291, 'number': 1065}
+- Overall Precision: 0.7245
+- Overall Recall: 0.7837
+- Overall F1: 0.7530
+- Overall Accuracy: 0.8069
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                        | Header                                                                                                         | Question                                                                                                     | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.7835        | 1.0   | 10   | 1.5696          | {'precision': 0.02753303964757709, 'recall': 0.030902348578491966, 'f1': 0.029120559114735003, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                    | {'precision': 0.23644444444444446, 'recall': 0.24976525821596243, 'f1': 0.24292237442922376, 'number': 1065} | 0.1431            | 0.1460         | 0.1446     | 0.4162           |
+| 1.4134        | 2.0   | 20   | 1.2167          | {'precision': 0.15942028985507245, 'recall': 0.13597033374536466, 'f1': 0.1467645096731154, 'number': 809}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                    | {'precision': 0.42325227963525835, 'recall': 0.5230046948356808, 'f1': 0.4678706425871483, 'number': 1065}   | 0.3322            | 0.3347         | 0.3334     | 0.5768           |
+| 1.0829        | 3.0   | 30   | 0.9351          | {'precision': 0.4783599088838269, 'recall': 0.519159456118665, 'f1': 0.4979253112033195, 'number': 809}       | {'precision': 0.034482758620689655, 'recall': 0.008403361344537815, 'f1': 0.013513513513513513, 'number': 119} | {'precision': 0.6103896103896104, 'recall': 0.6619718309859155, 'f1': 0.6351351351351351, 'number': 1065}    | 0.5461            | 0.5650         | 0.5554     | 0.7105           |
+| 0.8077        | 4.0   | 40   | 0.7702          | {'precision': 0.6122233930453108, 'recall': 0.7181705809641533, 'f1': 0.6609783845278726, 'number': 809}      | {'precision': 0.2033898305084746, 'recall': 0.10084033613445378, 'f1': 0.13483146067415733, 'number': 119}     | {'precision': 0.6381631037212985, 'recall': 0.7568075117370892, 'f1': 0.6924398625429553, 'number': 1065}    | 0.6160            | 0.7020         | 0.6562     | 0.7659           |
+| 0.6407        | 5.0   | 50   | 0.7146          | {'precision': 0.6491978609625668, 'recall': 0.7503090234857849, 'f1': 0.6961009174311926, 'number': 809}      | {'precision': 0.2948717948717949, 'recall': 0.19327731092436976, 'f1': 0.233502538071066, 'number': 119}       | {'precision': 0.6921221864951769, 'recall': 0.8084507042253521, 'f1': 0.7457773928107406, 'number': 1065}    | 0.6606            | 0.7481         | 0.7016     | 0.7869           |
+| 0.5585        | 6.0   | 60   | 0.6995          | {'precision': 0.673866090712743, 'recall': 0.7713226205191595, 'f1': 0.7193083573487031, 'number': 809}       | {'precision': 0.3372093023255814, 'recall': 0.24369747899159663, 'f1': 0.2829268292682927, 'number': 119}      | {'precision': 0.7374784110535406, 'recall': 0.8018779342723005, 'f1': 0.768331084120558, 'number': 1065}     | 0.6945            | 0.7561         | 0.7240     | 0.7948           |
+| 0.4934        | 7.0   | 70   | 0.6852          | {'precision': 0.6681222707423581, 'recall': 0.7564894932014833, 'f1': 0.7095652173913044, 'number': 809}      | {'precision': 0.37777777777777777, 'recall': 0.2857142857142857, 'f1': 0.3253588516746411, 'number': 119}      | {'precision': 0.7634408602150538, 'recall': 0.8, 'f1': 0.7812929848693261, 'number': 1065}                   | 0.7059            | 0.7516         | 0.7281     | 0.7979           |
+| 0.4384        | 8.0   | 80   | 0.6731          | {'precision': 0.6920492721164614, 'recall': 0.7639060568603214, 'f1': 0.7262044653349001, 'number': 809}      | {'precision': 0.3008130081300813, 'recall': 0.31092436974789917, 'f1': 0.3057851239669422, 'number': 119}      | {'precision': 0.7508503401360545, 'recall': 0.8291079812206573, 'f1': 0.788041053101294, 'number': 1065}     | 0.7016            | 0.7717         | 0.7350     | 0.8021           |
+| 0.3737        | 9.0   | 90   | 0.6766          | {'precision': 0.6993392070484582, 'recall': 0.7849196538936959, 'f1': 0.7396622015142692, 'number': 809}      | {'precision': 0.2992125984251969, 'recall': 0.31932773109243695, 'f1': 0.30894308943089427, 'number': 119}     | {'precision': 0.7890974084003575, 'recall': 0.8291079812206573, 'f1': 0.8086080586080587, 'number': 1065}    | 0.7224            | 0.7807         | 0.7504     | 0.8046           |
+| 0.341         | 10.0  | 100  | 0.6950          | {'precision': 0.6888888888888889, 'recall': 0.7663782447466008, 'f1': 0.7255705090696314, 'number': 809}      | {'precision': 0.3619047619047619, 'recall': 0.31932773109243695, 'f1': 0.33928571428571425, 'number': 119}     | {'precision': 0.7859030837004405, 'recall': 0.8375586854460094, 'f1': 0.8109090909090909, 'number': 1065}    | 0.7243            | 0.7777         | 0.7501     | 0.8088           |
+| 0.3178        | 11.0  | 110  | 0.6979          | {'precision': 0.7157534246575342, 'recall': 0.7750309023485785, 'f1': 0.7442136498516321, 'number': 809}      | {'precision': 0.375, 'recall': 0.35294117647058826, 'f1': 0.3636363636363636, 'number': 119}                   | {'precision': 0.7805092186128183, 'recall': 0.8347417840375587, 'f1': 0.8067150635208712, 'number': 1065}    | 0.7325            | 0.7817         | 0.7563     | 0.8059           |
+| 0.2998        | 12.0  | 120  | 0.7019          | {'precision': 0.7027624309392265, 'recall': 0.7861557478368356, 'f1': 0.7421236872812136, 'number': 809}      | {'precision': 0.32061068702290074, 'recall': 0.35294117647058826, 'f1': 0.336, 'number': 119}                  | {'precision': 0.7885816235504014, 'recall': 0.8300469483568075, 'f1': 0.808783165599268, 'number': 1065}     | 0.7242            | 0.7837         | 0.7528     | 0.8069           |
+| 0.2809        | 13.0  | 130  | 0.7056          | {'precision': 0.7177777777777777, 'recall': 0.7985166872682324, 'f1': 0.7559976594499708, 'number': 809}      | {'precision': 0.3565217391304348, 'recall': 0.3445378151260504, 'f1': 0.3504273504273504, 'number': 119}       | {'precision': 0.7911504424778761, 'recall': 0.8394366197183099, 'f1': 0.8145785876993167, 'number': 1065}    | 0.7371            | 0.7933         | 0.7641     | 0.8097           |
+| 0.2656        | 14.0  | 140  | 0.7117          | {'precision': 0.718609865470852, 'recall': 0.792336217552534, 'f1': 0.7536743092298648, 'number': 809}        | {'precision': 0.33884297520661155, 'recall': 0.3445378151260504, 'f1': 0.3416666666666667, 'number': 119}      | {'precision': 0.7888198757763976, 'recall': 0.8347417840375587, 'f1': 0.8111313868613138, 'number': 1065}    | 0.7341            | 0.7883         | 0.7602     | 0.8098           |
+| 0.2669        | 15.0  | 150  | 0.7152          | {'precision': 0.7134894091415831, 'recall': 0.7911001236093943, 'f1': 0.7502930832356389, 'number': 809}      | {'precision': 0.31007751937984496, 'recall': 0.33613445378151263, 'f1': 0.3225806451612903, 'number': 119}     | {'precision': 0.7805309734513274, 'recall': 0.828169014084507, 'f1': 0.8036446469248291, 'number': 1065}     | 0.7245            | 0.7837         | 0.7530     | 0.8069           |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

logs/events.out.tfevents.1702960215.1565981e5c7c.1077.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e293d6c6eea6264bba44f545ccf1499b08c188b7bda11dd3e731d25b755dbbd0
-size 12920
+oid sha256:cba28483044600da9a7aa1642c83487724930f0dbfa4b78d6644f56d5b92fc95
+size 14596

preprocessor_config.json

@@ -2,6 +2,13 @@
   "apply_ocr": true,
   "do_resize": true,
   "feature_extractor_type": "LayoutLMv2FeatureExtractor",
+  "image_processor_type": "LayoutLMv2ImageProcessor",
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv2Processor",
   "resample": 2,
-  "size": 224
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
 }

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,80 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "apply_ocr": false,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "only_label_first_subword": true,
+  "pad_token": "[PAD]",
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv2Processor",
+  "sep_token": "[SEP]",
+  "sep_token_box": [
+    1000,
+    1000,
+    1000,
+    1000
+  ],
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "LayoutLMv2Tokenizer",
+  "unk_token": "[UNK]"
+}