End of training

README.md

@@ -0,0 +1,79 @@
+---
+license: mit
+base_model: microsoft/layoutlm-base-uncased
+tags:
+- generated_from_trainer
+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 an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6794
+- Answer: {'precision': 0.7050592034445641, 'recall': 0.8096415327564895, 'f1': 0.7537399309551209, 'number': 809}
+- Header: {'precision': 0.2971014492753623, 'recall': 0.3445378151260504, 'f1': 0.31906614785992216, 'number': 119}
+- Question: {'precision': 0.7856502242152467, 'recall': 0.8225352112676056, 'f1': 0.8036697247706422, 'number': 1065}
+- Overall Precision: 0.7204
+- Overall Recall: 0.7888
+- Overall F1: 0.7531
+- Overall Accuracy: 0.8043
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.7235        | 1.0   | 10   | 1.5460          | {'precision': 0.024602026049204053, 'recall': 0.021013597033374538, 'f1': 0.02266666666666667, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.4123076923076923, 'recall': 0.2516431924882629, 'f1': 0.31253644314868806, 'number': 1065} | 0.2125            | 0.1430         | 0.1710     | 0.3788           |
+| 1.407         | 2.0   | 20   | 1.2205          | {'precision': 0.15948777648428406, 'recall': 0.16934487021013597, 'f1': 0.1642685851318945, 'number': 809}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.4168994413407821, 'recall': 0.5605633802816902, 'f1': 0.4781738085702843, 'number': 1065}  | 0.3197            | 0.3683         | 0.3423     | 0.5851           |
+| 1.0795        | 3.0   | 30   | 0.9267          | {'precision': 0.510934393638171, 'recall': 0.6353522867737948, 'f1': 0.5663911845730027, 'number': 809}       | {'precision': 0.1111111111111111, 'recall': 0.04201680672268908, 'f1': 0.06097560975609755, 'number': 119}  | {'precision': 0.5874476987447699, 'recall': 0.6591549295774648, 'f1': 0.6212389380530974, 'number': 1065}  | 0.5436            | 0.6126         | 0.5761     | 0.7163           |
+| 0.8244        | 4.0   | 40   | 0.7676          | {'precision': 0.6219758064516129, 'recall': 0.7626699629171817, 'f1': 0.6851749028317601, 'number': 809}      | {'precision': 0.2191780821917808, 'recall': 0.13445378151260504, 'f1': 0.16666666666666669, 'number': 119}  | {'precision': 0.6691666666666667, 'recall': 0.7539906103286385, 'f1': 0.7090507726269316, 'number': 1065}  | 0.6340            | 0.7205         | 0.6745     | 0.7652           |
+| 0.6702        | 5.0   | 50   | 0.7059          | {'precision': 0.6361848574237955, 'recall': 0.799752781211372, 'f1': 0.7086527929901425, 'number': 809}       | {'precision': 0.25773195876288657, 'recall': 0.21008403361344538, 'f1': 0.23148148148148145, 'number': 119} | {'precision': 0.7138018628281118, 'recall': 0.7915492957746478, 'f1': 0.7506678539626003, 'number': 1065}  | 0.6601            | 0.7602         | 0.7066     | 0.7714           |
+| 0.5695        | 6.0   | 60   | 0.6803          | {'precision': 0.6496424923391215, 'recall': 0.7861557478368356, 'f1': 0.7114093959731544, 'number': 809}      | {'precision': 0.25, 'recall': 0.2184873949579832, 'f1': 0.23318385650224216, 'number': 119}                 | {'precision': 0.7203098106712564, 'recall': 0.7859154929577464, 'f1': 0.7516838796587336, 'number': 1065}  | 0.6677            | 0.7521         | 0.7074     | 0.7823           |
+| 0.5039        | 7.0   | 70   | 0.6660          | {'precision': 0.6928034371643395, 'recall': 0.7972805933250927, 'f1': 0.7413793103448275, 'number': 809}      | {'precision': 0.2222222222222222, 'recall': 0.2689075630252101, 'f1': 0.24334600760456274, 'number': 119}   | {'precision': 0.7471466198419666, 'recall': 0.7990610328638498, 'f1': 0.7722323049001815, 'number': 1065}  | 0.6902            | 0.7667         | 0.7264     | 0.7893           |
+| 0.4396        | 8.0   | 80   | 0.6420          | {'precision': 0.6763485477178424, 'recall': 0.8059332509270705, 'f1': 0.7354765933446138, 'number': 809}      | {'precision': 0.23484848484848486, 'recall': 0.2605042016806723, 'f1': 0.24701195219123506, 'number': 119}  | {'precision': 0.7559523809523809, 'recall': 0.8347417840375587, 'f1': 0.7933958054439983, 'number': 1065}  | 0.6919            | 0.7888         | 0.7372     | 0.7965           |
+| 0.3747        | 9.0   | 90   | 0.6437          | {'precision': 0.6881606765327696, 'recall': 0.8046971569839307, 'f1': 0.7418803418803418, 'number': 809}      | {'precision': 0.22535211267605634, 'recall': 0.2689075630252101, 'f1': 0.24521072796934865, 'number': 119}  | {'precision': 0.7732506643046945, 'recall': 0.819718309859155, 'f1': 0.7958067456700091, 'number': 1065}   | 0.7018            | 0.7807         | 0.7392     | 0.7979           |
+| 0.3415        | 10.0  | 100  | 0.6580          | {'precision': 0.69989281886388, 'recall': 0.8071693448702101, 'f1': 0.7497129735935705, 'number': 809}        | {'precision': 0.23076923076923078, 'recall': 0.25210084033613445, 'f1': 0.24096385542168675, 'number': 119} | {'precision': 0.7621527777777778, 'recall': 0.8244131455399061, 'f1': 0.7920613441587732, 'number': 1065}  | 0.7047            | 0.7832         | 0.7419     | 0.8022           |
+| 0.3206        | 11.0  | 110  | 0.6671          | {'precision': 0.7009544008483564, 'recall': 0.8170580964153276, 'f1': 0.754566210045662, 'number': 809}       | {'precision': 0.2624113475177305, 'recall': 0.31092436974789917, 'f1': 0.2846153846153846, 'number': 119}   | {'precision': 0.7675628794449263, 'recall': 0.8309859154929577, 'f1': 0.7980162308385933, 'number': 1065}  | 0.7076            | 0.7943         | 0.7485     | 0.7997           |
+| 0.2974        | 12.0  | 120  | 0.6651          | {'precision': 0.7023809523809523, 'recall': 0.8022249690976514, 'f1': 0.7489901904212348, 'number': 809}      | {'precision': 0.3, 'recall': 0.35294117647058826, 'f1': 0.3243243243243243, 'number': 119}                  | {'precision': 0.7784697508896797, 'recall': 0.8215962441314554, 'f1': 0.7994518044769301, 'number': 1065}  | 0.7157            | 0.7858         | 0.7491     | 0.8040           |
+| 0.2809        | 13.0  | 130  | 0.6796          | {'precision': 0.7013669821240799, 'recall': 0.8244746600741656, 'f1': 0.7579545454545454, 'number': 809}      | {'precision': 0.273972602739726, 'recall': 0.33613445378151263, 'f1': 0.3018867924528302, 'number': 119}    | {'precision': 0.770999115826702, 'recall': 0.8187793427230047, 'f1': 0.7941712204007287, 'number': 1065}   | 0.7087            | 0.7923         | 0.7482     | 0.8014           |
+| 0.2664        | 14.0  | 140  | 0.6777          | {'precision': 0.6993534482758621, 'recall': 0.8022249690976514, 'f1': 0.7472654001151412, 'number': 809}      | {'precision': 0.2826086956521739, 'recall': 0.3277310924369748, 'f1': 0.3035019455252918, 'number': 119}    | {'precision': 0.785204991087344, 'recall': 0.8272300469483568, 'f1': 0.8056698673982624, 'number': 1065}   | 0.7171            | 0.7873         | 0.7505     | 0.8025           |
+| 0.2685        | 15.0  | 150  | 0.6794          | {'precision': 0.7050592034445641, 'recall': 0.8096415327564895, 'f1': 0.7537399309551209, 'number': 809}      | {'precision': 0.2971014492753623, 'recall': 0.3445378151260504, 'f1': 0.31906614785992216, 'number': 119}   | {'precision': 0.7856502242152467, 'recall': 0.8225352112676056, 'f1': 0.8036697247706422, 'number': 1065}  | 0.7204            | 0.7888         | 0.7531     | 0.8043           |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

logs/events.out.tfevents.1703685730.dlmachine2.183757.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a23463dab863db0fe76a66f37b8e5425269e040aaa0f68478429c0cfb486167
-size 13005
+oid sha256:cce80a601618b7a204954487d59ff7aa45c54c1b1227a42ac24464961de02683
+size 14681

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa9b994152400bcd38ebfbcb4064f81b973b829ecc42f2da237f5b7645d532d
+oid sha256:5f6e5237ce11ff1a3c9e4bccd6c3a1d01d81fdb731abb4af2275859d03e22f6d
 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]"
+}