End of training

README.md

@@ -0,0 +1,80 @@
+---
+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: 1.0686
+- Answer: {'precision': 0.36396724294813465, 'recall': 0.49443757725587145, 'f1': 0.41928721174004197, 'number': 809}
+- Header: {'precision': 0.27835051546391754, 'recall': 0.226890756302521, 'f1': 0.25, 'number': 119}
+- Question: {'precision': 0.5165991902834008, 'recall': 0.5990610328638498, 'f1': 0.5547826086956522, 'number': 1065}
+- Overall Precision: 0.4381
+- Overall Recall: 0.5344
+- Overall F1: 0.4815
+- Overall Accuracy: 0.6250
+
+## 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
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                      | Header                                                                                                      | Question                                                                                                    | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.6981        | 1.0   | 10   | 1.5076          | {'precision': 0.03027027027027027, 'recall': 0.034610630407911, 'f1': 0.032295271049596314, 'number': 809}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.2620056497175141, 'recall': 0.3483568075117371, 'f1': 0.29907295445384924, 'number': 1065}  | 0.1704            | 0.2002         | 0.1841     | 0.3875           |
+| 1.414         | 2.0   | 20   | 1.3021          | {'precision': 0.21108179419525067, 'recall': 0.39555006180469715, 'f1': 0.2752688172043011, 'number': 809}  | {'precision': 0.23076923076923078, 'recall': 0.12605042016806722, 'f1': 0.16304347826086957, 'number': 119} | {'precision': 0.29304029304029305, 'recall': 0.4507042253521127, 'f1': 0.35516093229744733, 'number': 1065} | 0.2532            | 0.4089         | 0.3127     | 0.4499           |
+| 1.2456        | 3.0   | 30   | 1.1694          | {'precision': 0.23877245508982037, 'recall': 0.3943139678615575, 'f1': 0.29743589743589743, 'number': 809}  | {'precision': 0.3333333333333333, 'recall': 0.17647058823529413, 'f1': 0.23076923076923078, 'number': 119}  | {'precision': 0.35604395604395606, 'recall': 0.6084507042253521, 'f1': 0.4492201039861352, 'number': 1065}  | 0.3069            | 0.4957         | 0.3791     | 0.5226           |
+| 1.1356        | 4.0   | 40   | 1.0684          | {'precision': 0.2732606873428332, 'recall': 0.40296662546353523, 'f1': 0.3256743256743257, 'number': 809}   | {'precision': 0.3333333333333333, 'recall': 0.23529411764705882, 'f1': 0.27586206896551724, 'number': 119}  | {'precision': 0.4185733512786003, 'recall': 0.584037558685446, 'f1': 0.48765190121520974, 'number': 1065}   | 0.3532            | 0.4897         | 0.4104     | 0.5856           |
+| 1.0269        | 5.0   | 50   | 1.0533          | {'precision': 0.29270462633451955, 'recall': 0.40667490729295425, 'f1': 0.3404035178479048, 'number': 809}  | {'precision': 0.2857142857142857, 'recall': 0.2184873949579832, 'f1': 0.24761904761904763, 'number': 119}   | {'precision': 0.4263959390862944, 'recall': 0.6309859154929578, 'f1': 0.5088981446421811, 'number': 1065}   | 0.3680            | 0.5153         | 0.4293     | 0.5925           |
+| 0.9574        | 6.0   | 60   | 1.0417          | {'precision': 0.31875, 'recall': 0.5043263288009888, 'f1': 0.3906175203446625, 'number': 809}               | {'precision': 0.2839506172839506, 'recall': 0.19327731092436976, 'f1': 0.22999999999999998, 'number': 119}  | {'precision': 0.5027173913043478, 'recall': 0.5211267605633803, 'f1': 0.5117565698478561, 'number': 1065}   | 0.4               | 0.4947         | 0.4424     | 0.6055           |
+| 0.8746        | 7.0   | 70   | 1.0403          | {'precision': 0.33510167992926615, 'recall': 0.4684796044499382, 'f1': 0.39072164948453614, 'number': 809}  | {'precision': 0.3023255813953488, 'recall': 0.2184873949579832, 'f1': 0.25365853658536586, 'number': 119}   | {'precision': 0.5072340425531915, 'recall': 0.5596244131455399, 'f1': 0.532142857142857, 'number': 1065}    | 0.4185            | 0.5023         | 0.4566     | 0.6148           |
+| 0.8197        | 8.0   | 80   | 1.0323          | {'precision': 0.3490304709141274, 'recall': 0.4672435105067985, 'f1': 0.3995771670190275, 'number': 809}    | {'precision': 0.25742574257425743, 'recall': 0.2184873949579832, 'f1': 0.23636363636363636, 'number': 119}  | {'precision': 0.49101796407185627, 'recall': 0.615962441314554, 'f1': 0.546438983756768, 'number': 1065}    | 0.4206            | 0.5319         | 0.4698     | 0.6212           |
+| 0.7517        | 9.0   | 90   | 1.0418          | {'precision': 0.3580705009276438, 'recall': 0.47713226205191595, 'f1': 0.4091149973502915, 'number': 809}   | {'precision': 0.27472527472527475, 'recall': 0.21008403361344538, 'f1': 0.2380952380952381, 'number': 119}  | {'precision': 0.5266323024054983, 'recall': 0.5755868544600939, 'f1': 0.5500224315836698, 'number': 1065}   | 0.4389            | 0.5138         | 0.4734     | 0.6237           |
+| 0.7561        | 10.0  | 100  | 1.0652          | {'precision': 0.3465587044534413, 'recall': 0.5290482076637825, 'f1': 0.4187866927592955, 'number': 809}    | {'precision': 0.29545454545454547, 'recall': 0.2184873949579832, 'f1': 0.251207729468599, 'number': 119}    | {'precision': 0.536697247706422, 'recall': 0.5492957746478874, 'f1': 0.5429234338747101, 'number': 1065}    | 0.4306            | 0.5213         | 0.4716     | 0.6226           |
+| 0.6786        | 11.0  | 110  | 1.0498          | {'precision': 0.3706896551724138, 'recall': 0.4783683559950556, 'f1': 0.4177010253642741, 'number': 809}    | {'precision': 0.3068181818181818, 'recall': 0.226890756302521, 'f1': 0.2608695652173913, 'number': 119}     | {'precision': 0.5236593059936908, 'recall': 0.6234741784037559, 'f1': 0.5692241748821258, 'number': 1065}   | 0.4492            | 0.5409         | 0.4908     | 0.6369           |
+| 0.6839        | 12.0  | 120  | 1.1004          | {'precision': 0.35621198957428324, 'recall': 0.5067985166872683, 'f1': 0.41836734693877553, 'number': 809}  | {'precision': 0.30851063829787234, 'recall': 0.24369747899159663, 'f1': 0.27230046948356806, 'number': 119} | {'precision': 0.5135350318471338, 'recall': 0.6056338028169014, 'f1': 0.5557949159844894, 'number': 1065}   | 0.4334            | 0.5439         | 0.4824     | 0.6115           |
+| 0.6505        | 13.0  | 130  | 1.0685          | {'precision': 0.3501303214596003, 'recall': 0.49814585908529047, 'f1': 0.41122448979591836, 'number': 809}  | {'precision': 0.26804123711340205, 'recall': 0.2184873949579832, 'f1': 0.24074074074074076, 'number': 119}  | {'precision': 0.5467756584922797, 'recall': 0.5652582159624413, 'f1': 0.5558633425669437, 'number': 1065}   | 0.4389            | 0.5173         | 0.4749     | 0.6324           |
+| 0.6221        | 14.0  | 140  | 1.0541          | {'precision': 0.3643192488262911, 'recall': 0.4796044499381953, 'f1': 0.4140875133404482, 'number': 809}    | {'precision': 0.2857142857142857, 'recall': 0.23529411764705882, 'f1': 0.2580645161290323, 'number': 119}   | {'precision': 0.5176747839748626, 'recall': 0.6187793427230047, 'f1': 0.5637296834901625, 'number': 1065}   | 0.4413            | 0.5394         | 0.4854     | 0.6316           |
+| 0.6015        | 15.0  | 150  | 1.0686          | {'precision': 0.36396724294813465, 'recall': 0.49443757725587145, 'f1': 0.41928721174004197, 'number': 809} | {'precision': 0.27835051546391754, 'recall': 0.226890756302521, 'f1': 0.25, 'number': 119}                  | {'precision': 0.5165991902834008, 'recall': 0.5990610328638498, 'f1': 0.5547826086956522, 'number': 1065}   | 0.4381            | 0.5344         | 0.4815     | 0.6250           |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

logs/events.out.tfevents.1709894034.0c59864ff64b.3471.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea82cdf7ebe73a76966eceb15ca49f9a33b42881753ae7869d61115bcbc6b29
-size 15385
+oid sha256:14236f68cc16e8115504145c784860248f71db9bd28e1041b92de61d800edce6
+size 15739

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d29e3d5bc8a62bed8a5e1c153e5af9c70ba433f98676f439cd394c4d49cbe16
+oid sha256:c25189f363d3bbc8b7d1d4b7f04f44024d19086d6d42b52aad0296d1d8ef4007
 size 450558212

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": 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]"
+}