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: 0.7045
+- Answer: {'precision': 0.7013274336283186, 'recall': 0.7836835599505563, 'f1': 0.7402218330414477, 'number': 809}
+- Header: {'precision': 0.3111111111111111, 'recall': 0.35294117647058826, 'f1': 0.33070866141732286, 'number': 119}
+- Question: {'precision': 0.773936170212766, 'recall': 0.819718309859155, 'f1': 0.796169630642955, 'number': 1065}
+- Overall Precision: 0.7148
+- Overall Recall: 0.7772
+- Overall F1: 0.7447
+- Overall Accuracy: 0.8045
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.8311        | 1.0   | 10   | 1.5893          | {'precision': 0.01643192488262911, 'recall': 0.0173053152039555, 'f1': 0.016857314870559904, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                   | {'precision': 0.23476005188067445, 'recall': 0.1699530516431925, 'f1': 0.19716775599128541, 'number': 1065} | 0.1201            | 0.0978         | 0.1079     | 0.3735           |
+| 1.453         | 2.0   | 20   | 1.2320          | {'precision': 0.16265750286368844, 'recall': 0.17552533992583436, 'f1': 0.16884661117717004, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                   | {'precision': 0.43330980945659847, 'recall': 0.5765258215962441, 'f1': 0.49476228847703463, 'number': 1065} | 0.3301            | 0.3793         | 0.3530     | 0.5937           |
+| 1.0885        | 3.0   | 30   | 0.9242          | {'precision': 0.4983991462113127, 'recall': 0.5772558714462299, 'f1': 0.5349369988545246, 'number': 809}    | {'precision': 0.05263157894736842, 'recall': 0.008403361344537815, 'f1': 0.014492753623188406, 'number': 119} | {'precision': 0.556745182012848, 'recall': 0.7323943661971831, 'f1': 0.632603406326034, 'number': 1065}     | 0.5295            | 0.6262         | 0.5738     | 0.7132           |
+| 0.8351        | 4.0   | 40   | 0.7984          | {'precision': 0.5991902834008097, 'recall': 0.7317676143386898, 'f1': 0.6588759042849194, 'number': 809}    | {'precision': 0.16, 'recall': 0.06722689075630252, 'f1': 0.09467455621301775, 'number': 119}                  | {'precision': 0.6562763268744735, 'recall': 0.7314553990610329, 'f1': 0.691829484902309, 'number': 1065}    | 0.6198            | 0.6919         | 0.6539     | 0.7574           |
+| 0.6746        | 5.0   | 50   | 0.7364          | {'precision': 0.6524663677130045, 'recall': 0.7194066749072929, 'f1': 0.6843033509700176, 'number': 809}    | {'precision': 0.21951219512195122, 'recall': 0.15126050420168066, 'f1': 0.1791044776119403, 'number': 119}    | {'precision': 0.6493212669683258, 'recall': 0.8084507042253521, 'f1': 0.7202007528230866, 'number': 1065}   | 0.6352            | 0.7331         | 0.6806     | 0.7789           |
+| 0.5833        | 6.0   | 60   | 0.7065          | {'precision': 0.6387487386478304, 'recall': 0.7824474660074165, 'f1': 0.7033333333333333, 'number': 809}    | {'precision': 0.25333333333333335, 'recall': 0.15966386554621848, 'f1': 0.1958762886597938, 'number': 119}    | {'precision': 0.7177489177489178, 'recall': 0.7784037558685446, 'f1': 0.7468468468468469, 'number': 1065}   | 0.6668            | 0.7431         | 0.7029     | 0.7837           |
+| 0.5101        | 7.0   | 70   | 0.6765          | {'precision': 0.6811751904243744, 'recall': 0.7737948084054388, 'f1': 0.724537037037037, 'number': 809}     | {'precision': 0.2564102564102564, 'recall': 0.25210084033613445, 'f1': 0.2542372881355932, 'number': 119}     | {'precision': 0.7319762510602206, 'recall': 0.8103286384976526, 'f1': 0.7691622103386809, 'number': 1065}   | 0.6858            | 0.7622         | 0.7220     | 0.7972           |
+| 0.4538        | 8.0   | 80   | 0.6643          | {'precision': 0.6775210084033614, 'recall': 0.7972805933250927, 'f1': 0.7325383304940376, 'number': 809}    | {'precision': 0.23893805309734514, 'recall': 0.226890756302521, 'f1': 0.2327586206896552, 'number': 119}      | {'precision': 0.7389830508474576, 'recall': 0.8187793427230047, 'f1': 0.7768374164810691, 'number': 1065}   | 0.6878            | 0.7747         | 0.7286     | 0.8014           |
+| 0.3958        | 9.0   | 90   | 0.6724          | {'precision': 0.7022222222222222, 'recall': 0.7812113720642769, 'f1': 0.7396138092451726, 'number': 809}    | {'precision': 0.25757575757575757, 'recall': 0.2857142857142857, 'f1': 0.27091633466135456, 'number': 119}    | {'precision': 0.7319932998324958, 'recall': 0.8206572769953052, 'f1': 0.7737937140327579, 'number': 1065}   | 0.6918            | 0.7727         | 0.7300     | 0.7994           |
+| 0.3902        | 10.0  | 100  | 0.6726          | {'precision': 0.6846071044133477, 'recall': 0.7861557478368356, 'f1': 0.7318757192174913, 'number': 809}    | {'precision': 0.288135593220339, 'recall': 0.2857142857142857, 'f1': 0.2869198312236287, 'number': 119}       | {'precision': 0.7652790079716564, 'recall': 0.8112676056338028, 'f1': 0.7876025524156791, 'number': 1065}   | 0.7050            | 0.7697         | 0.7359     | 0.8080           |
+| 0.3294        | 11.0  | 110  | 0.6827          | {'precision': 0.7018701870187019, 'recall': 0.788627935723115, 'f1': 0.7427240977881256, 'number': 809}     | {'precision': 0.28888888888888886, 'recall': 0.3277310924369748, 'f1': 0.3070866141732283, 'number': 119}     | {'precision': 0.7508561643835616, 'recall': 0.8234741784037559, 'f1': 0.7854903716972683, 'number': 1065}   | 0.7025            | 0.7797         | 0.7391     | 0.8032           |
+| 0.3124        | 12.0  | 120  | 0.6909          | {'precision': 0.6974697469746974, 'recall': 0.7836835599505563, 'f1': 0.7380675203725262, 'number': 809}    | {'precision': 0.3125, 'recall': 0.33613445378151263, 'f1': 0.3238866396761134, 'number': 119}                 | {'precision': 0.771960958296362, 'recall': 0.8169014084507042, 'f1': 0.7937956204379562, 'number': 1065}    | 0.7135            | 0.7747         | 0.7428     | 0.8047           |
+| 0.2965        | 13.0  | 130  | 0.6986          | {'precision': 0.7002212389380531, 'recall': 0.7824474660074165, 'f1': 0.7390542907180385, 'number': 809}    | {'precision': 0.3230769230769231, 'recall': 0.35294117647058826, 'f1': 0.3373493975903615, 'number': 119}     | {'precision': 0.7712014134275619, 'recall': 0.819718309859155, 'f1': 0.7947200728265817, 'number': 1065}    | 0.7147            | 0.7767         | 0.7444     | 0.8040           |
+| 0.2676        | 14.0  | 140  | 0.7010          | {'precision': 0.7028824833702882, 'recall': 0.7836835599505563, 'f1': 0.7410870835768557, 'number': 809}    | {'precision': 0.32575757575757575, 'recall': 0.36134453781512604, 'f1': 0.3426294820717131, 'number': 119}    | {'precision': 0.7768888888888889, 'recall': 0.8206572769953052, 'f1': 0.7981735159817351, 'number': 1065}   | 0.7184            | 0.7782         | 0.7471     | 0.8060           |
+| 0.2747        | 15.0  | 150  | 0.7045          | {'precision': 0.7013274336283186, 'recall': 0.7836835599505563, 'f1': 0.7402218330414477, 'number': 809}    | {'precision': 0.3111111111111111, 'recall': 0.35294117647058826, 'f1': 0.33070866141732286, 'number': 119}    | {'precision': 0.773936170212766, 'recall': 0.819718309859155, 'f1': 0.796169630642955, 'number': 1065}      | 0.7148            | 0.7772         | 0.7447     | 0.8045           |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

logs/events.out.tfevents.1718013889.4a153d784002.1470.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85db09fefebbcd9c4dbec289b75f5436595c0ac57b659d3cd0257caac206b468
-size 14915
+oid sha256:a1eba50279738ee8aabb9c981224233c895999f62b55d9c19f002aefadef0074
+size 15984

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "apply_ocr",
+    "ocr_lang",
+    "tesseract_config",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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]"
+}