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: 1.3725
+- Answer: {'precision': 0.07982261640798226, 'recall': 0.08899876390605686, 'f1': 0.0841613091759205, 'number': 809}
+- Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
+- Question: {'precision': 0.4174242424242424, 'recall': 0.5173708920187794, 'f1': 0.46205450733752623, 'number': 1065}
+- Overall Precision: 0.2804
+- Overall Recall: 0.3126
+- Overall F1: 0.2956
+- Overall Accuracy: 0.5437
+
+## 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-06
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.8773        | 1.0   | 10   | 1.8489          | {'precision': 0.00547645125958379, 'recall': 0.006180469715698393, 'f1': 0.005807200929152149, 'number': 809}   | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.04874446085672083, 'recall': 0.030985915492957747, 'f1': 0.03788748564867968, 'number': 1065} | 0.0227            | 0.0191         | 0.0207     | 0.2819           |
+| 1.807         | 2.0   | 20   | 1.7831          | {'precision': 0.005925925925925926, 'recall': 0.004944375772558714, 'f1': 0.005390835579514824, 'number': 809}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.06716417910447761, 'recall': 0.03380281690140845, 'f1': 0.04497189256714553, 'number': 1065}  | 0.0327            | 0.0201         | 0.0249     | 0.2996           |
+| 1.7516        | 3.0   | 30   | 1.7272          | {'precision': 0.0071633237822349575, 'recall': 0.006180469715698393, 'f1': 0.006635700066357001, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.10175438596491228, 'recall': 0.054460093896713614, 'f1': 0.0709480122324159, 'number': 1065}  | 0.0496            | 0.0316         | 0.0386     | 0.3189           |
+| 1.7057        | 4.0   | 40   | 1.6785          | {'precision': 0.012626262626262626, 'recall': 0.012360939431396786, 'f1': 0.012492192379762648, 'number': 809}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.16886930983847284, 'recall': 0.107981220657277, 'f1': 0.13172966781214204, 'number': 1065}    | 0.0849            | 0.0627         | 0.0721     | 0.3426           |
+| 1.6571        | 5.0   | 50   | 1.6336          | {'precision': 0.016286644951140065, 'recall': 0.018541409147095178, 'f1': 0.017341040462427744, 'number': 809}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.2211764705882353, 'recall': 0.17652582159624414, 'f1': 0.19634464751958225, 'number': 1065}   | 0.1146            | 0.1019         | 0.1079     | 0.3714           |
+| 1.6219        | 6.0   | 60   | 1.5894          | {'precision': 0.03238095238095238, 'recall': 0.042027194066749075, 'f1': 0.036578805809575045, 'number': 809}   | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.26129666011787817, 'recall': 0.24976525821596243, 'f1': 0.2554008641382621, 'number': 1065}   | 0.1451            | 0.1505         | 0.1477     | 0.4028           |
+| 1.5748        | 7.0   | 70   | 1.5484          | {'precision': 0.03796296296296296, 'recall': 0.05067985166872682, 'f1': 0.04340921122286924, 'number': 809}     | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.28073394495412846, 'recall': 0.28732394366197184, 'f1': 0.28399071925754066, 'number': 1065}  | 0.1599            | 0.1741         | 0.1667     | 0.4319           |
+| 1.5387        | 8.0   | 80   | 1.5098          | {'precision': 0.044036697247706424, 'recall': 0.059332509270704575, 'f1': 0.05055292259083728, 'number': 809}   | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.30583333333333335, 'recall': 0.34460093896713617, 'f1': 0.3240618101545254, 'number': 1065}   | 0.1812            | 0.2082         | 0.1938     | 0.4623           |
+| 1.5004        | 9.0   | 90   | 1.4753          | {'precision': 0.05149812734082397, 'recall': 0.06798516687268233, 'f1': 0.05860415556739478, 'number': 809}     | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.3378812199036918, 'recall': 0.39530516431924884, 'f1': 0.36434443963652097, 'number': 1065}   | 0.2057            | 0.2388         | 0.2210     | 0.4887           |
+| 1.4659        | 10.0  | 100  | 1.4462          | {'precision': 0.058823529411764705, 'recall': 0.0754017305315204, 'f1': 0.06608884073672806, 'number': 809}     | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.3586530931871574, 'recall': 0.4300469483568075, 'f1': 0.39111870196413323, 'number': 1065}    | 0.2243            | 0.2604         | 0.2410     | 0.5046           |
+| 1.4314        | 11.0  | 110  | 1.4207          | {'precision': 0.06769230769230769, 'recall': 0.0815822002472188, 'f1': 0.07399103139013452, 'number': 809}      | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.38271604938271603, 'recall': 0.46572769953051646, 'f1': 0.42016094875052945, 'number': 1065}  | 0.2475            | 0.2820         | 0.2636     | 0.5184           |
+| 1.4242        | 12.0  | 120  | 1.4003          | {'precision': 0.07203389830508475, 'recall': 0.08405438813349815, 'f1': 0.0775812892184826, 'number': 809}      | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.40076628352490423, 'recall': 0.49107981220657276, 'f1': 0.4413502109704641, 'number': 1065}   | 0.2628            | 0.2965         | 0.2786     | 0.5273           |
+| 1.3939        | 13.0  | 130  | 1.3855          | {'precision': 0.07792207792207792, 'recall': 0.08899876390605686, 'f1': 0.0830929024812464, 'number': 809}      | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.40953822861468586, 'recall': 0.507981220657277, 'f1': 0.45347862531433364, 'number': 1065}    | 0.2731            | 0.3076         | 0.2893     | 0.5367           |
+| 1.3837        | 14.0  | 140  | 1.3764          | {'precision': 0.08021978021978023, 'recall': 0.09023485784919653, 'f1': 0.08493310063990692, 'number': 809}     | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.41635124905374715, 'recall': 0.5164319248826291, 'f1': 0.4610226320201173, 'number': 1065}    | 0.2792            | 0.3126         | 0.2950     | 0.5410           |
+| 1.3603        | 15.0  | 150  | 1.3725          | {'precision': 0.07982261640798226, 'recall': 0.08899876390605686, 'f1': 0.0841613091759205, 'number': 809}      | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4174242424242424, 'recall': 0.5173708920187794, 'f1': 0.46205450733752623, 'number': 1065}    | 0.2804            | 0.3126         | 0.2956     | 0.5437           |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.0
+- Tokenizers 0.13.3

logs/events.out.tfevents.1690466940.fcb3ea2dcf27.4909.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3725f5416e98ed93ef3686600ae8632f0920239f7d598015bce909c07da879
-size 14072
+oid sha256:18fe7c613086565240243c0d46ee1c6f84bd3d4c32e87dc543f002f2bf1bc2f7
+size 14426

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 +1,7 @@
+{
+  "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]"
+}