End of training

README.md

@@ -0,0 +1,79 @@
+---
+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: 0.6878
+- Answer: {'precision': 0.7163198247535597, 'recall': 0.8084054388133498, 'f1': 0.7595818815331011, 'number': 809}
+- Header: {'precision': 0.2992125984251969, 'recall': 0.31932773109243695, 'f1': 0.30894308943089427, 'number': 119}
+- Question: {'precision': 0.7820738137082601, 'recall': 0.8356807511737089, 'f1': 0.8079891057648662, 'number': 1065}
+- Overall Precision: 0.7264
+- Overall Recall: 0.7938
+- Overall F1: 0.7586
+- Overall Accuracy: 0.8119
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.791         | 1.0   | 10   | 1.5434          | {'precision': 0.02383134738771769, 'recall': 0.032138442521631644, 'f1': 0.027368421052631577, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                  | {'precision': 0.1517094017094017, 'recall': 0.13333333333333333, 'f1': 0.14192903548225888, 'number': 1065} | 0.0829            | 0.0843         | 0.0836     | 0.4089           |
+| 1.4241        | 2.0   | 20   | 1.2209          | {'precision': 0.21506682867557717, 'recall': 0.21878862793572312, 'f1': 0.21691176470588236, 'number': 809}   | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                  | {'precision': 0.5193014705882353, 'recall': 0.5305164319248826, 'f1': 0.5248490478402229, 'number': 1065}   | 0.3883            | 0.3723         | 0.3801     | 0.6071           |
+| 1.0737        | 3.0   | 30   | 0.9131          | {'precision': 0.5521920668058455, 'recall': 0.65389369592089, 'f1': 0.5987549518958688, 'number': 809}        | {'precision': 0.10526315789473684, 'recall': 0.03361344537815126, 'f1': 0.050955414012738856, 'number': 119} | {'precision': 0.6549912434325744, 'recall': 0.7023474178403756, 'f1': 0.6778432260987766, 'number': 1065}   | 0.5992            | 0.6427         | 0.6202     | 0.7260           |
+| 0.8315        | 4.0   | 40   | 0.7824          | {'precision': 0.5840297121634169, 'recall': 0.7775030902348579, 'f1': 0.6670201484623542, 'number': 809}      | {'precision': 0.16, 'recall': 0.06722689075630252, 'f1': 0.09467455621301775, 'number': 119}                 | {'precision': 0.6850044365572315, 'recall': 0.7248826291079812, 'f1': 0.7043795620437956, 'number': 1065}   | 0.6251            | 0.7070         | 0.6635     | 0.7595           |
+| 0.6888        | 5.0   | 50   | 0.7225          | {'precision': 0.6345945945945946, 'recall': 0.7255871446229913, 'f1': 0.6770472895040369, 'number': 809}      | {'precision': 0.2631578947368421, 'recall': 0.16806722689075632, 'f1': 0.20512820512820512, 'number': 119}   | {'precision': 0.7260397830018083, 'recall': 0.7539906103286385, 'f1': 0.7397512666973746, 'number': 1065}   | 0.6692            | 0.7075         | 0.6878     | 0.7735           |
+| 0.5828        | 6.0   | 60   | 0.6844          | {'precision': 0.6371951219512195, 'recall': 0.7750309023485785, 'f1': 0.6993865030674846, 'number': 809}      | {'precision': 0.2716049382716049, 'recall': 0.18487394957983194, 'f1': 0.22, 'number': 119}                  | {'precision': 0.6926196269261963, 'recall': 0.8018779342723005, 'f1': 0.7432550043516102, 'number': 1065}   | 0.6540            | 0.7541         | 0.7005     | 0.7860           |
+| 0.5049        | 7.0   | 70   | 0.6662          | {'precision': 0.6692056583242655, 'recall': 0.7601977750309024, 'f1': 0.7118055555555556, 'number': 809}      | {'precision': 0.2903225806451613, 'recall': 0.226890756302521, 'f1': 0.25471698113207547, 'number': 119}     | {'precision': 0.7250213492741246, 'recall': 0.7971830985915493, 'f1': 0.759391771019678, 'number': 1065}    | 0.6830            | 0.7481         | 0.7141     | 0.7889           |
+| 0.456         | 8.0   | 80   | 0.6507          | {'precision': 0.6635610766045549, 'recall': 0.792336217552534, 'f1': 0.7222535211267606, 'number': 809}       | {'precision': 0.225, 'recall': 0.226890756302521, 'f1': 0.22594142259414227, 'number': 119}                  | {'precision': 0.730899830220713, 'recall': 0.8084507042253521, 'f1': 0.7677218011591618, 'number': 1065}    | 0.6754            | 0.7672         | 0.7183     | 0.7962           |
+| 0.3999        | 9.0   | 90   | 0.6468          | {'precision': 0.6928034371643395, 'recall': 0.7972805933250927, 'f1': 0.7413793103448275, 'number': 809}      | {'precision': 0.25, 'recall': 0.24369747899159663, 'f1': 0.24680851063829787, 'number': 119}                 | {'precision': 0.7611548556430446, 'recall': 0.8169014084507042, 'f1': 0.7880434782608696, 'number': 1065}   | 0.7050            | 0.7747         | 0.7382     | 0.8029           |
+| 0.3618        | 10.0  | 100  | 0.6543          | {'precision': 0.7033805888767721, 'recall': 0.7972805933250927, 'f1': 0.7473928157589804, 'number': 809}      | {'precision': 0.2689075630252101, 'recall': 0.2689075630252101, 'f1': 0.2689075630252101, 'number': 119}     | {'precision': 0.7706502636203867, 'recall': 0.8234741784037559, 'f1': 0.7961870177031322, 'number': 1065}   | 0.7148            | 0.7797         | 0.7459     | 0.8043           |
+| 0.3279        | 11.0  | 110  | 0.6608          | {'precision': 0.7040704070407041, 'recall': 0.7911001236093943, 'f1': 0.7450523864959255, 'number': 809}      | {'precision': 0.2773109243697479, 'recall': 0.2773109243697479, 'f1': 0.2773109243697479, 'number': 119}     | {'precision': 0.7676855895196506, 'recall': 0.8253521126760563, 'f1': 0.7954751131221719, 'number': 1065}   | 0.7142            | 0.7787         | 0.7451     | 0.8092           |
+| 0.3085        | 12.0  | 120  | 0.6735          | {'precision': 0.7003222341568206, 'recall': 0.8059332509270705, 'f1': 0.7494252873563217, 'number': 809}      | {'precision': 0.3076923076923077, 'recall': 0.3025210084033613, 'f1': 0.30508474576271183, 'number': 119}    | {'precision': 0.772609819121447, 'recall': 0.8422535211267606, 'f1': 0.8059299191374663, 'number': 1065}    | 0.7175            | 0.7953         | 0.7544     | 0.8084           |
+| 0.2933        | 13.0  | 130  | 0.6795          | {'precision': 0.7088331515812432, 'recall': 0.8034610630407911, 'f1': 0.7531865585168018, 'number': 809}      | {'precision': 0.2867647058823529, 'recall': 0.3277310924369748, 'f1': 0.30588235294117644, 'number': 119}    | {'precision': 0.7782764811490126, 'recall': 0.8140845070422535, 'f1': 0.7957778797613584, 'number': 1065}   | 0.7180            | 0.7807         | 0.7481     | 0.8099           |
+| 0.2742        | 14.0  | 140  | 0.6836          | {'precision': 0.7133550488599348, 'recall': 0.8121137206427689, 'f1': 0.7595375722543352, 'number': 809}      | {'precision': 0.3064516129032258, 'recall': 0.31932773109243695, 'f1': 0.31275720164609055, 'number': 119}   | {'precision': 0.784, 'recall': 0.828169014084507, 'f1': 0.8054794520547947, 'number': 1065}                 | 0.7267            | 0.7913         | 0.7576     | 0.8115           |
+| 0.2699        | 15.0  | 150  | 0.6878          | {'precision': 0.7163198247535597, 'recall': 0.8084054388133498, 'f1': 0.7595818815331011, 'number': 809}      | {'precision': 0.2992125984251969, 'recall': 0.31932773109243695, 'f1': 0.30894308943089427, 'number': 119}   | {'precision': 0.7820738137082601, 'recall': 0.8356807511737089, 'f1': 0.8079891057648662, 'number': 1065}   | 0.7264            | 0.7938         | 0.7586     | 0.8119           |
+
+
+### Framework versions
+
+- Transformers 4.33.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "apply_ocr": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv2FeatureExtractor",
+  "image_processor_type": "LayoutLMv2ImageProcessor",
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv2Processor",
+  "resample": 2,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdddca57ff4903c1ebb6f5f5e818ad4e1e383e98affcc5a668022ea3975df129
+oid sha256:2ced92370dddbab1b746730a7fd1910fc55f2e306539fa6786e5c0f6ed35c26e
 size 450603969

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "additional_special_tokens": null,
+  "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]"
+}