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: 0.6801
+- Answer: {'precision': 0.6998916576381365, 'recall': 0.7985166872682324, 'f1': 0.745958429561201, 'number': 809}
+- Header: {'precision': 0.30158730158730157, 'recall': 0.31932773109243695, 'f1': 0.310204081632653, 'number': 119}
+- Question: {'precision': 0.7674216027874564, 'recall': 0.8272300469483568, 'f1': 0.7962042476276546, 'number': 1065}
+- Overall Precision: 0.7123
+- Overall Recall: 0.7852
+- Overall F1: 0.7470
+- Overall Accuracy: 0.8102
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.8269        | 1.0   | 10   | 1.5983          | {'precision': 0.0274949083503055, 'recall': 0.03337453646477132, 'f1': 0.03015075376884422, 'number': 809}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.10761154855643044, 'recall': 0.07699530516431925, 'f1': 0.08976464148877941, 'number': 1065} | 0.0625            | 0.0547         | 0.0583     | 0.3800           |
+| 1.4969        | 2.0   | 20   | 1.3148          | {'precision': 0.14439140811455847, 'recall': 0.14956736711990112, 'f1': 0.14693381906496664, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.3501683501683502, 'recall': 0.39061032863849765, 'f1': 0.36928539724811366, 'number': 1065}  | 0.2651            | 0.2694         | 0.2672     | 0.5643           |
+| 1.1839        | 3.0   | 30   | 1.0447          | {'precision': 0.40492957746478875, 'recall': 0.4264524103831891, 'f1': 0.41541240216736913, 'number': 809}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.5461672473867596, 'recall': 0.5887323943661972, 'f1': 0.5666516041572526, 'number': 1065}    | 0.486             | 0.4877         | 0.4869     | 0.6655           |
+| 0.9261        | 4.0   | 40   | 0.8452          | {'precision': 0.5813715455475946, 'recall': 0.7021013597033374, 'f1': 0.6360582306830906, 'number': 809}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.6362068965517241, 'recall': 0.6929577464788732, 'f1': 0.6633707865168539, 'number': 1065}    | 0.6035            | 0.6553         | 0.6283     | 0.7335           |
+| 0.7296        | 5.0   | 50   | 0.7494          | {'precision': 0.6223849372384938, 'recall': 0.7354758961681088, 'f1': 0.6742209631728047, 'number': 809}    | {'precision': 0.16666666666666666, 'recall': 0.06722689075630252, 'f1': 0.09580838323353293, 'number': 119} | {'precision': 0.6773356401384083, 'recall': 0.7352112676056338, 'f1': 0.7050877982890591, 'number': 1065}    | 0.6417            | 0.6954         | 0.6675     | 0.7676           |
+| 0.6079        | 6.0   | 60   | 0.6998          | {'precision': 0.629399585921325, 'recall': 0.7515451174289246, 'f1': 0.6850704225352113, 'number': 809}     | {'precision': 0.12222222222222222, 'recall': 0.09243697478991597, 'f1': 0.10526315789473684, 'number': 119} | {'precision': 0.6630686198920586, 'recall': 0.8075117370892019, 'f1': 0.7281964436917865, 'number': 1065}    | 0.6286            | 0.7421         | 0.6806     | 0.7881           |
+| 0.5267        | 7.0   | 70   | 0.6732          | {'precision': 0.6366427840327533, 'recall': 0.7688504326328801, 'f1': 0.696528555431131, 'number': 809}     | {'precision': 0.20652173913043478, 'recall': 0.15966386554621848, 'f1': 0.1800947867298578, 'number': 119}  | {'precision': 0.7107296137339055, 'recall': 0.7774647887323943, 'f1': 0.7426008968609865, 'number': 1065}    | 0.6576            | 0.7371         | 0.6951     | 0.7864           |
+| 0.4762        | 8.0   | 80   | 0.6606          | {'precision': 0.6577319587628866, 'recall': 0.788627935723115, 'f1': 0.71725688589095, 'number': 809}       | {'precision': 0.25663716814159293, 'recall': 0.24369747899159663, 'f1': 0.25, 'number': 119}                | {'precision': 0.731665228645384, 'recall': 0.7962441314553991, 'f1': 0.762589928057554, 'number': 1065}      | 0.6757            | 0.7602         | 0.7155     | 0.7936           |
+| 0.4175        | 9.0   | 90   | 0.6566          | {'precision': 0.6815761448349308, 'recall': 0.7911001236093943, 'f1': 0.7322654462242563, 'number': 809}    | {'precision': 0.25892857142857145, 'recall': 0.24369747899159663, 'f1': 0.2510822510822511, 'number': 119}  | {'precision': 0.7513089005235603, 'recall': 0.8084507042253521, 'f1': 0.7788331071913162, 'number': 1065}    | 0.6964            | 0.7677         | 0.7303     | 0.8021           |
+| 0.374         | 10.0  | 100  | 0.6592          | {'precision': 0.6956521739130435, 'recall': 0.7911001236093943, 'f1': 0.7403123192596877, 'number': 809}    | {'precision': 0.319672131147541, 'recall': 0.3277310924369748, 'f1': 0.32365145228215775, 'number': 119}    | {'precision': 0.7637931034482759, 'recall': 0.831924882629108, 'f1': 0.7964044943820225, 'number': 1065}     | 0.7107            | 0.7852         | 0.7461     | 0.8070           |
+| 0.3406        | 11.0  | 110  | 0.6666          | {'precision': 0.7, 'recall': 0.796044499381953, 'f1': 0.7449392712550607, 'number': 809}                    | {'precision': 0.3305084745762712, 'recall': 0.3277310924369748, 'f1': 0.32911392405063294, 'number': 119}   | {'precision': 0.7656387665198238, 'recall': 0.815962441314554, 'f1': 0.79, 'number': 1065}                   | 0.7142            | 0.7787         | 0.7451     | 0.8071           |
+| 0.332         | 12.0  | 120  | 0.6704          | {'precision': 0.6941798941798942, 'recall': 0.8108776266996292, 'f1': 0.7480045610034207, 'number': 809}    | {'precision': 0.3220338983050847, 'recall': 0.31932773109243695, 'f1': 0.32067510548523204, 'number': 119}  | {'precision': 0.7660311958405546, 'recall': 0.8300469483568075, 'f1': 0.7967552951780081, 'number': 1065}    | 0.7118            | 0.7918         | 0.7496     | 0.8078           |
+| 0.3061        | 13.0  | 130  | 0.6787          | {'precision': 0.6908108108108109, 'recall': 0.7898640296662547, 'f1': 0.7370242214532873, 'number': 809}    | {'precision': 0.3253968253968254, 'recall': 0.3445378151260504, 'f1': 0.33469387755102037, 'number': 119}   | {'precision': 0.7669305189094108, 'recall': 0.8187793427230047, 'f1': 0.7920072661217076, 'number': 1065}    | 0.7093            | 0.7787         | 0.7424     | 0.8091           |
+| 0.2879        | 14.0  | 140  | 0.6781          | {'precision': 0.6951871657754011, 'recall': 0.8034610630407911, 'f1': 0.7454128440366973, 'number': 809}    | {'precision': 0.3333333333333333, 'recall': 0.33613445378151263, 'f1': 0.33472803347280333, 'number': 119}  | {'precision': 0.7746478873239436, 'recall': 0.8262910798122066, 'f1': 0.7996365288505224, 'number': 1065}    | 0.7166            | 0.7878         | 0.7505     | 0.8099           |
+| 0.2831        | 15.0  | 150  | 0.6801          | {'precision': 0.6998916576381365, 'recall': 0.7985166872682324, 'f1': 0.745958429561201, 'number': 809}     | {'precision': 0.30158730158730157, 'recall': 0.31932773109243695, 'f1': 0.310204081632653, 'number': 119}   | {'precision': 0.7674216027874564, 'recall': 0.8272300469483568, 'f1': 0.7962042476276546, 'number': 1065}    | 0.7123            | 0.7852         | 0.7470     | 0.8102           |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.2
+- Tokenizers 0.13.3

logs/events.out.tfevents.1691049198.65df036853ca.2258.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621e09fc4dc70326cd5f151fc9ba848a7133412888815bee3ed51e090a6efa0e
-size 14069
+oid sha256:d9fbfdd2d4d41565da4d2dfb8b5a5c72da904c6c9f2b2bbb83fe3162298c3c48
+size 14423

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 sha256:35a964e428bfdc08f78a3e2f3bba39637037f13b9d21f059faaf52b4fa8fc0cc
+oid sha256:7753bf1e62c451d8d5e735cc7904f4f3e4bcf84f5761a94155301aa2b1006a5a
 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]"
+}