End of training

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- funsd-layoutlmv3
+model-index:
+- name: layoutxlm
+  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. -->
+
+# layoutxlm
+
+This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the funsd-layoutlmv3 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5889
+- Answer: {'precision': 0.8761904761904762, 'recall': 0.9008567931456548, 'f1': 0.8883524441762222, 'number': 817}
+- Header: {'precision': 0.6666666666666666, 'recall': 0.5546218487394958, 'f1': 0.6055045871559633, 'number': 119}
+- Question: {'precision': 0.8883968113374667, 'recall': 0.9312906220984215, 'f1': 0.9093381686310064, 'number': 1077}
+- Overall Precision: 0.8728
+- Overall Recall: 0.8967
+- Overall F1: 0.8846
+- Overall Accuracy: 0.8115
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 2500
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Answer                                                                                                   | Header                                                                                                    | Question                                                                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.4322        | 10.53  | 200  | 0.9083          | {'precision': 0.7704569606801275, 'recall': 0.8873929008567931, 'f1': 0.8248009101251422, 'number': 817} | {'precision': 0.6162790697674418, 'recall': 0.44537815126050423, 'f1': 0.5170731707317073, 'number': 119} | {'precision': 0.866852886405959, 'recall': 0.8644382544103992, 'f1': 0.8656438865643886, 'number': 1077}  | 0.8134            | 0.8490         | 0.8308     | 0.7863           |
+| 0.0467        | 21.05  | 400  | 1.2942          | {'precision': 0.8496583143507973, 'recall': 0.9130966952264382, 'f1': 0.88023598820059, 'number': 817}   | {'precision': 0.6585365853658537, 'recall': 0.453781512605042, 'f1': 0.5373134328358209, 'number': 119}   | {'precision': 0.8859964093357271, 'recall': 0.9164345403899722, 'f1': 0.9009584664536742, 'number': 1077} | 0.8616            | 0.8877         | 0.8745     | 0.7966           |
+| 0.015         | 31.58  | 600  | 1.2662          | {'precision': 0.8574739281575898, 'recall': 0.9057527539779682, 'f1': 0.880952380952381, 'number': 817}  | {'precision': 0.5304347826086957, 'recall': 0.5126050420168067, 'f1': 0.5213675213675214, 'number': 119}  | {'precision': 0.8793879387938794, 'recall': 0.9071494893221913, 'f1': 0.8930530164533822, 'number': 1077} | 0.8511            | 0.8833         | 0.8669     | 0.8114           |
+| 0.0081        | 42.11  | 800  | 1.5223          | {'precision': 0.8710462287104623, 'recall': 0.8763769889840881, 'f1': 0.8737034777303235, 'number': 817} | {'precision': 0.5882352941176471, 'recall': 0.5882352941176471, 'f1': 0.5882352941176471, 'number': 119}  | {'precision': 0.8885844748858448, 'recall': 0.903435468895079, 'f1': 0.8959484346224678, 'number': 1077}  | 0.8639            | 0.8738         | 0.8689     | 0.8041           |
+| 0.0033        | 52.63  | 1000 | 1.4361          | {'precision': 0.8502304147465438, 'recall': 0.9033047735618115, 'f1': 0.8759643916913946, 'number': 817} | {'precision': 0.6144578313253012, 'recall': 0.42857142857142855, 'f1': 0.504950495049505, 'number': 119}  | {'precision': 0.8767605633802817, 'recall': 0.924791086350975, 'f1': 0.9001355625847266, 'number': 1077}  | 0.8553            | 0.8867         | 0.8707     | 0.8156           |
+| 0.0026        | 63.16  | 1200 | 1.4994          | {'precision': 0.8615560640732265, 'recall': 0.9216646266829865, 'f1': 0.8905972797161442, 'number': 817} | {'precision': 0.5981308411214953, 'recall': 0.5378151260504201, 'f1': 0.5663716814159291, 'number': 119}  | {'precision': 0.8945454545454545, 'recall': 0.9136490250696379, 'f1': 0.9039963252181902, 'number': 1077} | 0.8654            | 0.8947         | 0.8798     | 0.8208           |
+| 0.0016        | 73.68  | 1400 | 1.6091          | {'precision': 0.858139534883721, 'recall': 0.9033047735618115, 'f1': 0.8801431127012522, 'number': 817}  | {'precision': 0.5980392156862745, 'recall': 0.5126050420168067, 'f1': 0.5520361990950226, 'number': 119}  | {'precision': 0.8947849954254345, 'recall': 0.9080779944289693, 'f1': 0.9013824884792625, 'number': 1077} | 0.8647            | 0.8828         | 0.8736     | 0.8167           |
+| 0.0009        | 84.21  | 1600 | 1.6010          | {'precision': 0.859122401847575, 'recall': 0.9106487148102815, 'f1': 0.8841354723707664, 'number': 817}  | {'precision': 0.6741573033707865, 'recall': 0.5042016806722689, 'f1': 0.576923076923077, 'number': 119}   | {'precision': 0.8882931188561215, 'recall': 0.9229340761374187, 'f1': 0.9052823315118397, 'number': 1077} | 0.8669            | 0.8932         | 0.8799     | 0.8049           |
+| 0.0006        | 94.74  | 1800 | 1.5889          | {'precision': 0.8761904761904762, 'recall': 0.9008567931456548, 'f1': 0.8883524441762222, 'number': 817} | {'precision': 0.6666666666666666, 'recall': 0.5546218487394958, 'f1': 0.6055045871559633, 'number': 119}  | {'precision': 0.8883968113374667, 'recall': 0.9312906220984215, 'f1': 0.9093381686310064, 'number': 1077} | 0.8728            | 0.8967         | 0.8846     | 0.8115           |
+| 0.0004        | 105.26 | 2000 | 1.6126          | {'precision': 0.8634772462077013, 'recall': 0.9057527539779682, 'f1': 0.8841099163679809, 'number': 817} | {'precision': 0.6538461538461539, 'recall': 0.5714285714285714, 'f1': 0.6098654708520179, 'number': 119}  | {'precision': 0.894404332129964, 'recall': 0.9201485608170845, 'f1': 0.9070938215102976, 'number': 1077}  | 0.8695            | 0.8937         | 0.8814     | 0.8127           |
+| 0.0004        | 115.79 | 2200 | 1.6606          | {'precision': 0.8403648802736602, 'recall': 0.9020807833537332, 'f1': 0.8701298701298701, 'number': 817} | {'precision': 0.6509433962264151, 'recall': 0.5798319327731093, 'f1': 0.6133333333333333, 'number': 119}  | {'precision': 0.8884826325411335, 'recall': 0.9025069637883009, 'f1': 0.8954398894518655, 'number': 1077} | 0.8560            | 0.8833         | 0.8694     | 0.7906           |
+| 0.0002        | 126.32 | 2400 | 1.6619          | {'precision': 0.8378684807256236, 'recall': 0.9045287637698899, 'f1': 0.8699234844025897, 'number': 817} | {'precision': 0.6836734693877551, 'recall': 0.5630252100840336, 'f1': 0.6175115207373272, 'number': 119}  | {'precision': 0.881981981981982, 'recall': 0.9090064995357474, 'f1': 0.8952903520804755, 'number': 1077}  | 0.8541            | 0.8867         | 0.8701     | 0.7929           |
+
+
+### Framework versions
+
+- Transformers 4.30.2
+- Pytorch 2.1.0.dev20230523+cu117
+- Datasets 2.13.0
+- Tokenizers 0.13.3

logs/events.out.tfevents.1687173916.9b4009781a6d.7847.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3302a7fbecb8367fa651f61f5b45b73c78ba1dae6ee0d6b2a8c9ae8c69044613
-size 12324
+oid sha256:37b195ff2521aa932210c2bd5cda0f56b322e6918b37bacdb41fb32389b53a36
+size 12678

logs/events.out.tfevents.1687175790.9b4009781a6d.7847.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a464f7f0a2f85d38d7986763a79aac8778617e37e1751d25d55cf0f1255b6ce1
+size 592

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "apply_ocr": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3FeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0886d980fe12526e6ed20ebad915168a653e20dcb8c09187843034c802330968
+oid sha256:a6531fd1796dc2bafd0a2cc633be3a13bda96d834a450dd52e8a0a840588f14d
 size 520821642

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "only_label_first_subword": true,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5abe2ea1bd5485b85ac5d6f9fde75e11eb48c1b4cb7e9b26423eb510d2ed70
+oid sha256:1791b788a77d7b9c49ecdbb7b002945a8d6c1ffb55cb23bab985b276f6b3e14d
 size 4404