End of training

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: 1.0370
+- Answer: {'precision': 0.39444995044598613, 'recall': 0.4919653893695921, 'f1': 0.43784378437843785, 'number': 809}
+- Header: {'precision': 0.26548672566371684, 'recall': 0.25210084033613445, 'f1': 0.25862068965517243, 'number': 119}
+- Question: {'precision': 0.5051546391752577, 'recall': 0.644131455399061, 'f1': 0.566240198101527, 'number': 1065}
+- Overall Precision: 0.4492
+- Overall Recall: 0.5590
+- Overall F1: 0.4981
+- Overall Accuracy: 0.6347
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.7638        | 1.0   | 10   | 1.5767          | {'precision': 0.02685284640171858, 'recall': 0.030902348578491966, 'f1': 0.028735632183908046, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.23186119873817035, 'recall': 0.13802816901408452, 'f1': 0.17304296645085343, 'number': 1065} | 0.1099            | 0.0863         | 0.0967     | 0.3463           |
+| 1.4838        | 2.0   | 20   | 1.3817          | {'precision': 0.20173267326732675, 'recall': 0.40296662546353523, 'f1': 0.2688659793814433, 'number': 809}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.27599486521181, 'recall': 0.40375586854460094, 'f1': 0.3278688524590164, 'number': 1065}     | 0.2365            | 0.3793         | 0.2913     | 0.4223           |
+| 1.2933        | 3.0   | 30   | 1.2178          | {'precision': 0.22845691382765532, 'recall': 0.4227441285537701, 'f1': 0.29661751951431053, 'number': 809}    | {'precision': 0.1076923076923077, 'recall': 0.058823529411764705, 'f1': 0.07608695652173912, 'number': 119} | {'precision': 0.3385542168674699, 'recall': 0.5276995305164319, 'f1': 0.4124770642201835, 'number': 1065}    | 0.2827            | 0.4571         | 0.3494     | 0.4903           |
+| 1.1591        | 4.0   | 40   | 1.1134          | {'precision': 0.2775800711743772, 'recall': 0.4820766378244747, 'f1': 0.3523035230352303, 'number': 809}      | {'precision': 0.27848101265822783, 'recall': 0.18487394957983194, 'f1': 0.2222222222222222, 'number': 119}  | {'precision': 0.37922077922077924, 'recall': 0.5483568075117371, 'f1': 0.4483685220729367, 'number': 1065}   | 0.3294            | 0.4997         | 0.3971     | 0.5555           |
+| 1.0602        | 5.0   | 50   | 1.0998          | {'precision': 0.2914764079147641, 'recall': 0.47342398022249693, 'f1': 0.3608101742816769, 'number': 809}     | {'precision': 0.3146067415730337, 'recall': 0.23529411764705882, 'f1': 0.2692307692307692, 'number': 119}   | {'precision': 0.4076227390180879, 'recall': 0.5924882629107981, 'f1': 0.4829697665518562, 'number': 1065}    | 0.3531            | 0.5228         | 0.4215     | 0.5676           |
+| 0.9666        | 6.0   | 60   | 1.2008          | {'precision': 0.3184044786564031, 'recall': 0.5624227441285538, 'f1': 0.4066130473637176, 'number': 809}      | {'precision': 0.36666666666666664, 'recall': 0.18487394957983194, 'f1': 0.24581005586592175, 'number': 119} | {'precision': 0.46556233653007845, 'recall': 0.5014084507042254, 'f1': 0.4828209764918625, 'number': 1065}   | 0.3835            | 0.5073         | 0.4368     | 0.5518           |
+| 0.9177        | 7.0   | 70   | 1.0682          | {'precision': 0.33756345177664976, 'recall': 0.4932014833127318, 'f1': 0.4008036162732296, 'number': 809}     | {'precision': 0.2978723404255319, 'recall': 0.23529411764705882, 'f1': 0.2629107981220657, 'number': 119}   | {'precision': 0.4583333333333333, 'recall': 0.5784037558685446, 'f1': 0.5114155251141553, 'number': 1065}    | 0.3981            | 0.5233         | 0.4522     | 0.5949           |
+| 0.8429        | 8.0   | 80   | 1.0318          | {'precision': 0.35264227642276424, 'recall': 0.4289245982694685, 'f1': 0.3870607919687674, 'number': 809}     | {'precision': 0.2909090909090909, 'recall': 0.2689075630252101, 'f1': 0.2794759825327511, 'number': 119}    | {'precision': 0.4475703324808184, 'recall': 0.6572769953051644, 'f1': 0.5325218714340054, 'number': 1065}    | 0.4059            | 0.5414         | 0.4640     | 0.6117           |
+| 0.8062        | 9.0   | 90   | 1.0339          | {'precision': 0.37058823529411766, 'recall': 0.4672435105067985, 'f1': 0.41334062329141613, 'number': 809}    | {'precision': 0.275, 'recall': 0.2773109243697479, 'f1': 0.27615062761506276, 'number': 119}                | {'precision': 0.4913728432108027, 'recall': 0.6150234741784038, 'f1': 0.5462885738115096, 'number': 1065}    | 0.4311            | 0.5349         | 0.4774     | 0.6213           |
+| 0.7862        | 10.0  | 100  | 1.0501          | {'precision': 0.35284552845528455, 'recall': 0.5364647713226205, 'f1': 0.42569887199607653, 'number': 809}    | {'precision': 0.3048780487804878, 'recall': 0.21008403361344538, 'f1': 0.24875621890547264, 'number': 119}  | {'precision': 0.4933852140077821, 'recall': 0.5953051643192488, 'f1': 0.5395744680851065, 'number': 1065}    | 0.4209            | 0.5484         | 0.4763     | 0.6103           |
+| 0.7206        | 11.0  | 110  | 1.0571          | {'precision': 0.3714020427112349, 'recall': 0.49443757725587145, 'f1': 0.4241781548250265, 'number': 809}     | {'precision': 0.2962962962962963, 'recall': 0.2689075630252101, 'f1': 0.28193832599118945, 'number': 119}   | {'precision': 0.5184893784421715, 'recall': 0.6187793427230047, 'f1': 0.5642123287671232, 'number': 1065}    | 0.4442            | 0.5474         | 0.4904     | 0.6234           |
+| 0.7242        | 12.0  | 120  | 1.0352          | {'precision': 0.3682771194165907, 'recall': 0.49938195302843014, 'f1': 0.4239244491080797, 'number': 809}     | {'precision': 0.3333333333333333, 'recall': 0.2689075630252101, 'f1': 0.29767441860465116, 'number': 119}   | {'precision': 0.4966984592809978, 'recall': 0.6356807511737089, 'f1': 0.557660626029654, 'number': 1065}     | 0.4354            | 0.5585         | 0.4893     | 0.6251           |
+| 0.6858        | 13.0  | 130  | 1.0447          | {'precision': 0.37962962962962965, 'recall': 0.5067985166872683, 'f1': 0.4340921122286925, 'number': 809}     | {'precision': 0.2672413793103448, 'recall': 0.2605042016806723, 'f1': 0.26382978723404255, 'number': 119}   | {'precision': 0.5022058823529412, 'recall': 0.6413145539906103, 'f1': 0.5632989690721649, 'number': 1065}    | 0.4397            | 0.5640         | 0.4942     | 0.6298           |
+| 0.6549        | 14.0  | 140  | 1.0332          | {'precision': 0.3821892393320965, 'recall': 0.5092707045735476, 'f1': 0.43667196608373077, 'number': 809}     | {'precision': 0.3263157894736842, 'recall': 0.2605042016806723, 'f1': 0.2897196261682243, 'number': 119}    | {'precision': 0.5044843049327354, 'recall': 0.6338028169014085, 'f1': 0.5617977528089888, 'number': 1065}    | 0.4452            | 0.5610         | 0.4964     | 0.6354           |
+| 0.6462        | 15.0  | 150  | 1.0370          | {'precision': 0.39444995044598613, 'recall': 0.4919653893695921, 'f1': 0.43784378437843785, 'number': 809}    | {'precision': 0.26548672566371684, 'recall': 0.25210084033613445, 'f1': 0.25862068965517243, 'number': 119} | {'precision': 0.5051546391752577, 'recall': 0.644131455399061, 'f1': 0.566240198101527, 'number': 1065}      | 0.4492            | 0.5590         | 0.4981     | 0.6347           |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

logs/events.out.tfevents.1710902016.6e1e6ed48043.12592.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10060ef85fd095cae3a70437b0ab3d65471de1f5f22a58647efd741dccb24fd
-size 14669
+oid sha256:a33a7bd831bf0cdba75a569d6353fe80f6a4dc7cc625b29ffc3a90842595d07f
+size 15738

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42de91b95e3229c5e56cb01f34eff0f84cc583965f975ccfa6233be4a52f2f6f
+oid sha256:cdcdec7a2711b4f830f7c8efb018a82a0796bc43132f61110e550ef2106e35c4
 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]"
+}