Training in progress, epoch 1

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
+  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: 1.1153
+- Answer: {'precision': 0.3834652594547054, 'recall': 0.5389369592088998, 'f1': 0.44809866392600206, 'number': 809}
+- Header: {'precision': 0.29347826086956524, 'recall': 0.226890756302521, 'f1': 0.2559241706161137, 'number': 119}
+- Question: {'precision': 0.5310457516339869, 'recall': 0.6103286384976526, 'f1': 0.5679335954565312, 'number': 1065}
+- Overall Precision: 0.4537
+- Overall Recall: 0.5585
+- Overall F1: 0.5007
+- Overall Accuracy: 0.6247
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.7836        | 1.0   | 10   | 1.5583          | {'precision': 0.03470919324577861, 'recall': 0.04573547589616811, 'f1': 0.039466666666666664, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                    | {'precision': 0.1947049089906233, 'recall': 0.3314553990610329, 'f1': 0.24530924252953445, 'number': 1065} | 0.1355            | 0.1957         | 0.1601     | 0.3600           |
+| 1.4728        | 2.0   | 20   | 1.3281          | {'precision': 0.1966216216216216, 'recall': 0.35970333745364647, 'f1': 0.25425950196592395, 'number': 809}   | {'precision': 0.017543859649122806, 'recall': 0.008403361344537815, 'f1': 0.011363636363636362, 'number': 119} | {'precision': 0.2851758793969849, 'recall': 0.4262910798122066, 'f1': 0.34173880316146027, 'number': 1065} | 0.2384            | 0.3743         | 0.2913     | 0.4276           |
+| 1.2767        | 3.0   | 30   | 1.1812          | {'precision': 0.24393624393624394, 'recall': 0.43510506798516685, 'f1': 0.3126110124333925, 'number': 809}   | {'precision': 0.21052631578947367, 'recall': 0.16806722689075632, 'f1': 0.1869158878504673, 'number': 119}     | {'precision': 0.36664584634603375, 'recall': 0.5511737089201878, 'f1': 0.4403600900225056, 'number': 1065} | 0.3055            | 0.4812         | 0.3737     | 0.4924           |
+| 1.1394        | 4.0   | 40   | 1.1120          | {'precision': 0.28407350689127103, 'recall': 0.45859085290482077, 'f1': 0.35082742316784865, 'number': 809}  | {'precision': 0.24691358024691357, 'recall': 0.16806722689075632, 'f1': 0.2, 'number': 119}                    | {'precision': 0.47240802675585286, 'recall': 0.5305164319248826, 'f1': 0.4997788589119858, 'number': 1065} | 0.3701            | 0.4797         | 0.4178     | 0.5608           |
+| 1.0619        | 5.0   | 50   | 1.1166          | {'precision': 0.29784454604833444, 'recall': 0.5636588380716935, 'f1': 0.38974358974358975, 'number': 809}   | {'precision': 0.30303030303030304, 'recall': 0.16806722689075632, 'f1': 0.21621621621621626, 'number': 119}    | {'precision': 0.4780621572212066, 'recall': 0.49107981220657276, 'f1': 0.4844835572024085, 'number': 1065} | 0.3712            | 0.5013         | 0.4266     | 0.5636           |
+| 0.9741        | 6.0   | 60   | 1.0751          | {'precision': 0.33383010432190763, 'recall': 0.553770086526576, 'f1': 0.4165504416550442, 'number': 809}     | {'precision': 0.2676056338028169, 'recall': 0.15966386554621848, 'f1': 0.19999999999999998, 'number': 119}     | {'precision': 0.5021570319240725, 'recall': 0.5464788732394367, 'f1': 0.5233812949640289, 'number': 1065}  | 0.4079            | 0.5263         | 0.4596     | 0.5844           |
+| 0.907         | 7.0   | 70   | 1.0587          | {'precision': 0.3643835616438356, 'recall': 0.4932014833127318, 'f1': 0.41911764705882354, 'number': 809}    | {'precision': 0.2125, 'recall': 0.14285714285714285, 'f1': 0.1708542713567839, 'number': 119}                  | {'precision': 0.5027624309392266, 'recall': 0.5981220657276995, 'f1': 0.5463121783876502, 'number': 1065}  | 0.4312            | 0.5283         | 0.4749     | 0.6038           |
+| 0.8469        | 8.0   | 80   | 1.1514          | {'precision': 0.365814696485623, 'recall': 0.5661310259579728, 'f1': 0.4444444444444444, 'number': 809}      | {'precision': 0.25, 'recall': 0.16806722689075632, 'f1': 0.20100502512562815, 'number': 119}                   | {'precision': 0.5555555555555556, 'recall': 0.4788732394366197, 'f1': 0.5143721633888049, 'number': 1065}  | 0.4391            | 0.4957         | 0.4657     | 0.5893           |
+| 0.7877        | 9.0   | 90   | 1.0944          | {'precision': 0.37608318890814557, 'recall': 0.5364647713226205, 'f1': 0.44218033622007136, 'number': 809}   | {'precision': 0.2558139534883721, 'recall': 0.18487394957983194, 'f1': 0.21463414634146344, 'number': 119}     | {'precision': 0.531934306569343, 'recall': 0.5474178403755868, 'f1': 0.5395650161962054, 'number': 1065}   | 0.4448            | 0.5213         | 0.4800     | 0.6101           |
+| 0.7464        | 10.0  | 100  | 1.0861          | {'precision': 0.3794642857142857, 'recall': 0.5253399258343634, 'f1': 0.4406428201140487, 'number': 809}     | {'precision': 0.24444444444444444, 'recall': 0.18487394957983194, 'f1': 0.21052631578947367, 'number': 119}    | {'precision': 0.5038699690402477, 'recall': 0.6112676056338028, 'f1': 0.5523971149766653, 'number': 1065}  | 0.4388            | 0.5509         | 0.4885     | 0.6188           |
+| 0.7109        | 11.0  | 110  | 1.0985          | {'precision': 0.3770491803278688, 'recall': 0.5401730531520396, 'f1': 0.44410569105691056, 'number': 809}    | {'precision': 0.30120481927710846, 'recall': 0.21008403361344538, 'f1': 0.24752475247524758, 'number': 119}    | {'precision': 0.5317725752508361, 'recall': 0.5971830985915493, 'f1': 0.5625829279080052, 'number': 1065}  | 0.4504            | 0.5509         | 0.4956     | 0.6204           |
+| 0.6833        | 12.0  | 120  | 1.1252          | {'precision': 0.380327868852459, 'recall': 0.5735475896168108, 'f1': 0.45736816165598815, 'number': 809}     | {'precision': 0.2967032967032967, 'recall': 0.226890756302521, 'f1': 0.2571428571428572, 'number': 119}        | {'precision': 0.5510018214936248, 'recall': 0.568075117370892, 'f1': 0.559408229311142, 'number': 1065}    | 0.4550            | 0.5499         | 0.4980     | 0.6213           |
+| 0.6591        | 13.0  | 130  | 1.1009          | {'precision': 0.38546458141674333, 'recall': 0.5179233621755254, 'f1': 0.4419831223628692, 'number': 809}    | {'precision': 0.25742574257425743, 'recall': 0.2184873949579832, 'f1': 0.23636363636363636, 'number': 119}     | {'precision': 0.5226400613967767, 'recall': 0.6394366197183099, 'f1': 0.575168918918919, 'number': 1065}   | 0.4520            | 0.5650         | 0.5022     | 0.6212           |
+| 0.639         | 14.0  | 140  | 1.1190          | {'precision': 0.3828125, 'recall': 0.484548825710754, 'f1': 0.42771412984178947, 'number': 809}              | {'precision': 0.2755102040816326, 'recall': 0.226890756302521, 'f1': 0.2488479262672811, 'number': 119}        | {'precision': 0.5295527156549521, 'recall': 0.6225352112676056, 'f1': 0.5722917565817868, 'number': 1065}  | 0.4558            | 0.5429         | 0.4955     | 0.6197           |
+| 0.6544        | 15.0  | 150  | 1.1153          | {'precision': 0.3834652594547054, 'recall': 0.5389369592088998, 'f1': 0.44809866392600206, 'number': 809}    | {'precision': 0.29347826086956524, 'recall': 0.226890756302521, 'f1': 0.2559241706161137, 'number': 119}       | {'precision': 0.5310457516339869, 'recall': 0.6103286384976526, 'f1': 0.5679335954565312, 'number': 1065}  | 0.4537            | 0.5585         | 0.5007     | 0.6247           |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.0

logs/events.out.tfevents.1711515807.DESKTOP-3M5IIL5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd2c6e5d51346c4931fe7ea4a74d268aeb0ea8c317b3780995cf48d56b3276a
-size 4757
+oid sha256:b7303cc18bc41955c6c87eca1e49c5ec9cc79b3d9e517507d9a052ce173e21e6
+size 14681

logs/events.out.tfevents.1711516332.DESKTOP-3M5IIL5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876ca6fdeb58824c75835144a30bf6272f72627f777ef3359e4351e9cf901044
+size 4757

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad65ef5185b8fe4c112324da214b7bed38f28326d8159ca6a49031a8173828d3
+oid sha256:0daa5562b7f36a291a4a4b46c0359cc9317126800f9b771185e1dbef9ff64c6e
 size 450558212

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": ""
+}

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]"
+}