End of training

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/layoutlm-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- funsd
+model-index:
+- name: layoutlm-funsd
+  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
+
+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: 0.6975
+- Answer: {'precision': 0.7057522123893806, 'recall': 0.788627935723115, 'f1': 0.7448920023350847, 'number': 809}
+- Header: {'precision': 0.2748091603053435, 'recall': 0.3025210084033613, 'f1': 0.288, 'number': 119}
+- Question: {'precision': 0.7804232804232805, 'recall': 0.8309859154929577, 'f1': 0.8049113233287858, 'number': 1065}
+- Overall Precision: 0.7188
+- Overall Recall: 0.7822
+- Overall F1: 0.7492
+- Overall Accuracy: 0.8031
+
+## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.8422        | 1.0   | 10   | 1.6206          | {'precision': 0.025280898876404494, 'recall': 0.022249690976514216, 'f1': 0.023668639053254437, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                   | {'precision': 0.2301255230125523, 'recall': 0.15492957746478872, 'f1': 0.18518518518518517, 'number': 1065} | 0.1277            | 0.0918         | 0.1068     | 0.3520           |
+| 1.4509        | 2.0   | 20   | 1.2639          | {'precision': 0.15125, 'recall': 0.14956736711990112, 'f1': 0.15040397762585456, 'number': 809}                | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                   | {'precision': 0.465642683912692, 'recall': 0.5408450704225352, 'f1': 0.5004344048653345, 'number': 1065}    | 0.3420            | 0.3497         | 0.3458     | 0.5726           |
+| 1.1141        | 3.0   | 30   | 0.9554          | {'precision': 0.5079872204472844, 'recall': 0.5896168108776267, 'f1': 0.5457665903890161, 'number': 809}       | {'precision': 0.07894736842105263, 'recall': 0.025210084033613446, 'f1': 0.038216560509554146, 'number': 119} | {'precision': 0.6070007955449482, 'recall': 0.7164319248826291, 'f1': 0.6571920757967269, 'number': 1065}   | 0.5564            | 0.6237         | 0.5881     | 0.7246           |
+| 0.8541        | 4.0   | 40   | 0.7774          | {'precision': 0.5957446808510638, 'recall': 0.69221260815822, 'f1': 0.6403659233847913, 'number': 809}         | {'precision': 0.19117647058823528, 'recall': 0.1092436974789916, 'f1': 0.13903743315508021, 'number': 119}    | {'precision': 0.6491228070175439, 'recall': 0.7643192488262911, 'f1': 0.7020267356619233, 'number': 1065}   | 0.6132            | 0.6959         | 0.6519     | 0.7636           |
+| 0.6793        | 5.0   | 50   | 0.7244          | {'precision': 0.6372549019607843, 'recall': 0.723114956736712, 'f1': 0.677475390851187, 'number': 809}         | {'precision': 0.23076923076923078, 'recall': 0.15126050420168066, 'f1': 0.18274111675126906, 'number': 119}   | {'precision': 0.6705516705516705, 'recall': 0.8103286384976526, 'f1': 0.733843537414966, 'number': 1065}    | 0.6421            | 0.7356         | 0.6857     | 0.7706           |
+| 0.5888        | 6.0   | 60   | 0.6842          | {'precision': 0.6595517609391676, 'recall': 0.7639060568603214, 'f1': 0.7079037800687286, 'number': 809}       | {'precision': 0.2597402597402597, 'recall': 0.16806722689075632, 'f1': 0.20408163265306123, 'number': 119}    | {'precision': 0.7196339434276207, 'recall': 0.812206572769953, 'f1': 0.7631230701367445, 'number': 1065}    | 0.6782            | 0.7541         | 0.7142     | 0.7847           |
+| 0.5107        | 7.0   | 70   | 0.6648          | {'precision': 0.6694473409801877, 'recall': 0.7935723114956736, 'f1': 0.7262443438914026, 'number': 809}       | {'precision': 0.24561403508771928, 'recall': 0.23529411764705882, 'f1': 0.24034334763948498, 'number': 119}   | {'precision': 0.7504347826086957, 'recall': 0.8103286384976526, 'f1': 0.779232505643341, 'number': 1065}    | 0.6896            | 0.7692         | 0.7272     | 0.7944           |
+| 0.455         | 8.0   | 80   | 0.6582          | {'precision': 0.6750788643533123, 'recall': 0.7935723114956736, 'f1': 0.7295454545454545, 'number': 809}       | {'precision': 0.25961538461538464, 'recall': 0.226890756302521, 'f1': 0.242152466367713, 'number': 119}       | {'precision': 0.75, 'recall': 0.8253521126760563, 'f1': 0.7858739383102369, 'number': 1065}                 | 0.6951            | 0.7767         | 0.7336     | 0.7990           |
+| 0.4012        | 9.0   | 90   | 0.6598          | {'precision': 0.6955093099671413, 'recall': 0.7849196538936959, 'f1': 0.7375145180023228, 'number': 809}       | {'precision': 0.25203252032520324, 'recall': 0.2605042016806723, 'f1': 0.25619834710743805, 'number': 119}    | {'precision': 0.7566409597257926, 'recall': 0.8291079812206573, 'f1': 0.7912186379928315, 'number': 1065}   | 0.7031            | 0.7772         | 0.7383     | 0.7989           |
+| 0.3934        | 10.0  | 100  | 0.6706          | {'precision': 0.7069716775599129, 'recall': 0.8022249690976514, 'f1': 0.751592356687898, 'number': 809}        | {'precision': 0.27586206896551724, 'recall': 0.2689075630252101, 'f1': 0.27234042553191484, 'number': 119}    | {'precision': 0.7775784753363228, 'recall': 0.8140845070422535, 'f1': 0.7954128440366972, 'number': 1065}   | 0.7203            | 0.7767         | 0.7475     | 0.8052           |
+| 0.3354        | 11.0  | 110  | 0.6780          | {'precision': 0.7046688382193268, 'recall': 0.8022249690976514, 'f1': 0.7502890173410405, 'number': 809}       | {'precision': 0.272, 'recall': 0.2857142857142857, 'f1': 0.27868852459016397, 'number': 119}                  | {'precision': 0.7675628794449263, 'recall': 0.8309859154929577, 'f1': 0.7980162308385933, 'number': 1065}   | 0.7131            | 0.7868         | 0.7481     | 0.8028           |
+| 0.3187        | 12.0  | 120  | 0.6842          | {'precision': 0.7097130242825607, 'recall': 0.7948084054388134, 'f1': 0.7498542274052479, 'number': 809}       | {'precision': 0.26717557251908397, 'recall': 0.29411764705882354, 'f1': 0.28, 'number': 119}                  | {'precision': 0.7742504409171076, 'recall': 0.8244131455399061, 'f1': 0.7985447930877672, 'number': 1065}   | 0.7167            | 0.7807         | 0.7474     | 0.8021           |
+| 0.3007        | 13.0  | 130  | 0.6944          | {'precision': 0.704225352112676, 'recall': 0.8034610630407911, 'f1': 0.7505773672055426, 'number': 809}        | {'precision': 0.2833333333333333, 'recall': 0.2857142857142857, 'f1': 0.2845188284518828, 'number': 119}      | {'precision': 0.7791519434628975, 'recall': 0.828169014084507, 'f1': 0.8029130632680928, 'number': 1065}    | 0.72              | 0.7858         | 0.7514     | 0.8022           |
+| 0.2805        | 14.0  | 140  | 0.7007          | {'precision': 0.7126948775055679, 'recall': 0.7911001236093943, 'f1': 0.7498535442296427, 'number': 809}       | {'precision': 0.2695035460992908, 'recall': 0.31932773109243695, 'f1': 0.2923076923076923, 'number': 119}     | {'precision': 0.7805530776092774, 'recall': 0.8215962441314554, 'f1': 0.8005489478499542, 'number': 1065}   | 0.7190            | 0.7792         | 0.7479     | 0.8010           |
+| 0.2795        | 15.0  | 150  | 0.6975          | {'precision': 0.7057522123893806, 'recall': 0.788627935723115, 'f1': 0.7448920023350847, 'number': 809}        | {'precision': 0.2748091603053435, 'recall': 0.3025210084033613, 'f1': 0.288, 'number': 119}                   | {'precision': 0.7804232804232805, 'recall': 0.8309859154929577, 'f1': 0.8049113233287858, 'number': 1065}   | 0.7188            | 0.7822         | 0.7492     | 0.8031           |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

logs/events.out.tfevents.1734081453.01a1eae8aae2.1475.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c5b0946bfb0b68ee282674af703317e5a1d4d2622f63f29f1dfa584cf5f054
-size 14436
+oid sha256:966240f91ca519e780a84d0428ad6add51c33f0e6e553dba0d6ba4109249f8b0
+size 16220

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "apply_ocr": true,
+  "do_resize": true,
+  "image_processor_type": "LayoutLMv2ImageProcessor",
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv2Processor",
+  "resample": 2,
+  "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": false,
+  "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]"
+}