End of training

README.md

@@ -0,0 +1,73 @@
+---
+license: cc-by-nc-sa-4.0
+tags:
+- generated_from_trainer
+model-index:
+- name: layoutlmv3-real_triplet
+  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. -->
+
+# layoutlmv3-real_triplet
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0166
+- Item: {'precision': 0.944560669456067, 'recall': 0.9495268138801262, 'f1': 0.9470372312532774, 'number': 951}
+- Aption: {'precision': 0.9277436946148603, 'recall': 0.9249065579340808, 'f1': 0.9263229538880381, 'number': 2943}
+- Ootnote: {'precision': 0.8297872340425532, 'recall': 0.8068965517241379, 'f1': 0.8181818181818181, 'number': 145}
+- Ormula: {'precision': 0.9745836985100789, 'recall': 0.9754385964912281, 'f1': 0.9750109601052169, 'number': 2280}
+- Overall Precision: 0.9450
+- Overall Recall: 0.9441
+- Overall F1: 0.9446
+- Overall Accuracy: 0.9980
+
+## 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: 8
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Item                                                                                                     | Aption                                                                                                    | Ootnote                                                                                                  | Ormula                                                                                                    | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.0173        | 1.0   | 8507  | 0.0103          | {'precision': 0.9440175631174533, 'recall': 0.9043112513144059, 'f1': 0.9237379162191193, 'number': 951} | {'precision': 0.9030054644808743, 'recall': 0.8984029901461094, 'f1': 0.9006983478112757, 'number': 2943} | {'precision': 0.7337662337662337, 'recall': 0.7793103448275862, 'f1': 0.7558528428093645, 'number': 145} | {'precision': 0.9664195377235063, 'recall': 0.9719298245614035, 'f1': 0.9691668488956922, 'number': 2280} | 0.9279            | 0.9231         | 0.9255     | 0.9975           |
+| 0.0072        | 2.0   | 17014 | 0.0121          | {'precision': 0.9393305439330544, 'recall': 0.9442691903259727, 'f1': 0.9417933927635028, 'number': 951} | {'precision': 0.9193493730938664, 'recall': 0.9218484539585458, 'f1': 0.9205972175093315, 'number': 2943} | {'precision': 0.7651006711409396, 'recall': 0.7862068965517242, 'f1': 0.7755102040816326, 'number': 145} | {'precision': 0.9686820356676816, 'recall': 0.9767543859649123, 'f1': 0.9727014632015725, 'number': 2280} | 0.9366            | 0.9419         | 0.9392     | 0.9977           |
+| 0.0056        | 3.0   | 25521 | 0.0104          | {'precision': 0.9389067524115756, 'recall': 0.9211356466876972, 'f1': 0.9299363057324842, 'number': 951} | {'precision': 0.9154160982264665, 'recall': 0.9119945633707102, 'f1': 0.9137021276595745, 'number': 2943} | {'precision': 0.6842105263157895, 'recall': 0.8068965517241379, 'f1': 0.7405063291139241, 'number': 145} | {'precision': 0.973568281938326, 'recall': 0.9692982456140351, 'f1': 0.9714285714285714, 'number': 2280}  | 0.9336            | 0.9316         | 0.9326     | 0.9978           |
+| 0.004         | 4.0   | 34028 | 0.0120          | {'precision': 0.9771428571428571, 'recall': 0.8990536277602523, 'f1': 0.9364731653888281, 'number': 951} | {'precision': 0.9220199244245963, 'recall': 0.9119945633707102, 'f1': 0.9169798428425008, 'number': 2943} | {'precision': 0.8214285714285714, 'recall': 0.7931034482758621, 'f1': 0.8070175438596492, 'number': 145} | {'precision': 0.9733158355205599, 'recall': 0.9758771929824561, 'f1': 0.9745948313622427, 'number': 2280} | 0.9464            | 0.9304         | 0.9383     | 0.9981           |
+| 0.0028        | 5.0   | 42535 | 0.0122          | {'precision': 0.9588431590656284, 'recall': 0.9064143007360673, 'f1': 0.9318918918918919, 'number': 951} | {'precision': 0.924378453038674, 'recall': 0.909616038056405, 'f1': 0.9169378318205172, 'number': 2943}   | {'precision': 0.8984375, 'recall': 0.7931034482758621, 'f1': 0.8424908424908425, 'number': 145}          | {'precision': 0.971453667105841, 'recall': 0.9701754385964912, 'f1': 0.9708141321044547, 'number': 2280}  | 0.9461            | 0.9283         | 0.9371     | 0.9980           |
+| 0.0022        | 6.0   | 51042 | 0.0161          | {'precision': 0.899009900990099, 'recall': 0.9547844374342797, 'f1': 0.9260581336053034, 'number': 951}  | {'precision': 0.9120916133378242, 'recall': 0.9201495073054706, 'f1': 0.9161028416779432, 'number': 2943} | {'precision': 0.8538461538461538, 'recall': 0.7655172413793103, 'f1': 0.8072727272727271, 'number': 145} | {'precision': 0.9733275032794053, 'recall': 0.9763157894736842, 'f1': 0.9748193562513685, 'number': 2280} | 0.9307            | 0.9421         | 0.9364     | 0.9978           |
+| 0.0015        | 7.0   | 59549 | 0.0187          | {'precision': 0.9438444924406048, 'recall': 0.9190325972660357, 'f1': 0.9312733084709643, 'number': 951} | {'precision': 0.9206730769230769, 'recall': 0.9109751953788651, 'f1': 0.9157984628522631, 'number': 2943} | {'precision': 0.875968992248062, 'recall': 0.7793103448275862, 'f1': 0.8248175182481752, 'number': 145}  | {'precision': 0.9741681260945709, 'recall': 0.9758771929824561, 'f1': 0.9750219106047328, 'number': 2280} | 0.9427            | 0.9326         | 0.9376     | 0.9981           |
+| 0.0012        | 8.0   | 68056 | 0.0145          | {'precision': 0.9401260504201681, 'recall': 0.9411146161934806, 'f1': 0.9406200735680504, 'number': 951} | {'precision': 0.9231032125768968, 'recall': 0.9177709819911655, 'f1': 0.9204293746805248, 'number': 2943} | {'precision': 0.8041958041958042, 'recall': 0.7931034482758621, 'f1': 0.7986111111111112, 'number': 145} | {'precision': 0.9753629564452265, 'recall': 0.9723684210526315, 'f1': 0.9738633867779486, 'number': 2280} | 0.9418            | 0.9381         | 0.9400     | 0.9981           |
+| 0.0009        | 9.0   | 76563 | 0.0140          | {'precision': 0.9475890985324947, 'recall': 0.9505783385909569, 'f1': 0.9490813648293962, 'number': 951} | {'precision': 0.9295003422313484, 'recall': 0.9228678219503907, 'f1': 0.9261722080136402, 'number': 2943} | {'precision': 0.8740740740740741, 'recall': 0.8137931034482758, 'f1': 0.8428571428571429, 'number': 145} | {'precision': 0.9771025979744606, 'recall': 0.9732456140350877, 'f1': 0.975170292243463, 'number': 2280}  | 0.9483            | 0.9427         | 0.9455     | 0.9980           |
+| 0.0007        | 10.0  | 85070 | 0.0166          | {'precision': 0.944560669456067, 'recall': 0.9495268138801262, 'f1': 0.9470372312532774, 'number': 951}  | {'precision': 0.9277436946148603, 'recall': 0.9249065579340808, 'f1': 0.9263229538880381, 'number': 2943} | {'precision': 0.8297872340425532, 'recall': 0.8068965517241379, 'f1': 0.8181818181818181, 'number': 145} | {'precision': 0.9745836985100789, 'recall': 0.9754385964912281, 'f1': 0.9750109601052169, 'number': 2280} | 0.9450            | 0.9441         | 0.9446     | 0.9980           |
+
+
+### Framework versions
+
+- Transformers 4.26.0
+- Pytorch 1.12.1
+- Datasets 2.9.0
+- Tokenizers 0.13.2

logs/events.out.tfevents.1679991505.138-2-233-57.101000.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd29faca9a14b60d168fd4f1afea599f699ca45d23cec4022fe889db5e2033d
-size 11349
+oid sha256:8aabcfac03edf0fe4be6bc06732dda2d5ac0eff90b61fd826c98a75411d9c64f
+size 11709

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3ImageProcessor",
+  "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 sha256:5d3463bb4651d1b032b602dc7dd064d6391cce41d24f41d93bc618f56fa82bcf
+oid sha256:b3289f01fbab1e1b9a4a74a18ffe83f1d34cf8eaa3432cd831387a8260f1efea
 size 503781199

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 +1,87 @@
+{
+  "add_prefix_space": true,
+  "apply_ocr": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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,
+  "name_or_path": "microsoft/layoutlmv3-base",
+  "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
+  ],
+  "special_tokens_map_file": null,
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}