Training in progress, epoch 1

README.md

@@ -1,3 +1,80 @@
 ---
 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: 1.0844
+- Answer: {'precision': 0.3143100511073254, 'recall': 0.4561186650185414, 'f1': 0.3721633888048412, 'number': 809}
+- Header: {'precision': 0.275, 'recall': 0.18487394957983194, 'f1': 0.22110552763819097, 'number': 119}
+- Question: {'precision': 0.44804716285924834, 'recall': 0.5708920187793427, 'f1': 0.5020644095788603, 'number': 1065}
+- Overall Precision: 0.3826
+- Overall Recall: 0.5013
+- Overall F1: 0.4340
+- Overall Accuracy: 0.5793
+
+## 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: 32
+- eval_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.7974        | 1.0   | 5    | 1.6082          | {'precision': 0.015957446808510637, 'recall': 0.003708281829419036, 'f1': 0.006018054162487462, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.13218390804597702, 'recall': 0.0215962441314554, 'f1': 0.037126715092816794, 'number': 1065} | 0.0718            | 0.0130         | 0.0221     | 0.2950           |
+| 1.6031        | 2.0   | 10   | 1.4809          | {'precision': 0.09702549575070822, 'recall': 0.16934487021013597, 'f1': 0.12336785231877535, 'number': 809}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.2448499117127722, 'recall': 0.39061032863849765, 'f1': 0.301013024602026, 'number': 1065}    | 0.1778            | 0.2775         | 0.2167     | 0.3926           |
+| 1.4415        | 3.0   | 15   | 1.3965          | {'precision': 0.15503875968992248, 'recall': 0.32138442521631644, 'f1': 0.20917135961383748, 'number': 809}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.25329341317365267, 'recall': 0.3971830985915493, 'f1': 0.3093235831809872, 'number': 1065}   | 0.2041            | 0.3427         | 0.2558     | 0.4162           |
+| 1.3417        | 4.0   | 20   | 1.2882          | {'precision': 0.1925233644859813, 'recall': 0.3819530284301607, 'f1': 0.25600662800331403, 'number': 809}      | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.2921832884097035, 'recall': 0.5089201877934272, 'f1': 0.3712328767123288, 'number': 1065}    | 0.2457            | 0.4270         | 0.3120     | 0.4305           |
+| 1.2673        | 5.0   | 25   | 1.2461          | {'precision': 0.2402555910543131, 'recall': 0.4647713226205192, 'f1': 0.3167649536647009, 'number': 809}       | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.3362183754993342, 'recall': 0.47417840375586856, 'f1': 0.39345539540319435, 'number': 1065}  | 0.2828            | 0.4420         | 0.3449     | 0.4621           |
+| 1.1953        | 6.0   | 30   | 1.1667          | {'precision': 0.2396469789545146, 'recall': 0.4363411619283066, 'f1': 0.30937773882559155, 'number': 809}      | {'precision': 0.1038961038961039, 'recall': 0.06722689075630252, 'f1': 0.08163265306122448, 'number': 119}  | {'precision': 0.34711246200607904, 'recall': 0.536150234741784, 'f1': 0.42140221402214023, 'number': 1065}   | 0.2917            | 0.4676         | 0.3593     | 0.5048           |
+| 1.1257        | 7.0   | 35   | 1.1238          | {'precision': 0.271211022480058, 'recall': 0.4622991347342398, 'f1': 0.34186471663619744, 'number': 809}       | {'precision': 0.17708333333333334, 'recall': 0.14285714285714285, 'f1': 0.15813953488372096, 'number': 119} | {'precision': 0.38812154696132595, 'recall': 0.5276995305164319, 'f1': 0.4472741742936729, 'number': 1065}   | 0.3260            | 0.4782         | 0.3877     | 0.5539           |
+| 1.0703        | 8.0   | 40   | 1.0882          | {'precision': 0.2758340113913751, 'recall': 0.41903584672435107, 'f1': 0.33267909715407257, 'number': 809}     | {'precision': 0.1919191919191919, 'recall': 0.15966386554621848, 'f1': 0.17431192660550457, 'number': 119}  | {'precision': 0.4045307443365696, 'recall': 0.5868544600938967, 'f1': 0.47892720306513414, 'number': 1065}   | 0.3422            | 0.4932         | 0.4040     | 0.5809           |
+| 1.0172        | 9.0   | 45   | 1.0768          | {'precision': 0.277602523659306, 'recall': 0.43510506798516685, 'f1': 0.3389504092441021, 'number': 809}       | {'precision': 0.24096385542168675, 'recall': 0.16806722689075632, 'f1': 0.19801980198019803, 'number': 119} | {'precision': 0.40967092008059103, 'recall': 0.5727699530516432, 'f1': 0.4776820673453407, 'number': 1065}   | 0.3458            | 0.4927         | 0.4064     | 0.5803           |
+| 0.9713        | 10.0  | 50   | 1.0884          | {'precision': 0.3041700735895339, 'recall': 0.45982694684796044, 'f1': 0.3661417322834645, 'number': 809}      | {'precision': 0.2631578947368421, 'recall': 0.16806722689075632, 'f1': 0.20512820512820512, 'number': 119}  | {'precision': 0.4506024096385542, 'recall': 0.5267605633802817, 'f1': 0.4857142857142857, 'number': 1065}    | 0.3746            | 0.4782         | 0.4201     | 0.5781           |
+| 0.9434        | 11.0  | 55   | 1.1220          | {'precision': 0.29082426127527217, 'recall': 0.4622991347342398, 'f1': 0.35704057279236273, 'number': 809}     | {'precision': 0.2727272727272727, 'recall': 0.17647058823529413, 'f1': 0.21428571428571427, 'number': 119}  | {'precision': 0.4404934687953556, 'recall': 0.5699530516431925, 'f1': 0.4969300040933278, 'number': 1065}    | 0.3656            | 0.5028         | 0.4233     | 0.5669           |
+| 0.9288        | 12.0  | 60   | 1.0876          | {'precision': 0.298372513562387, 'recall': 0.4079110012360939, 'f1': 0.34464751958224543, 'number': 809}       | {'precision': 0.23958333333333334, 'recall': 0.19327731092436976, 'f1': 0.21395348837209302, 'number': 119} | {'precision': 0.4299933642999336, 'recall': 0.6084507042253521, 'f1': 0.5038880248833593, 'number': 1065}    | 0.3695            | 0.5023         | 0.4258     | 0.5784           |
+| 0.9043        | 13.0  | 65   | 1.1185          | {'precision': 0.31703204047217537, 'recall': 0.4647713226205192, 'f1': 0.3769423558897243, 'number': 809}      | {'precision': 0.2894736842105263, 'recall': 0.18487394957983194, 'f1': 0.22564102564102564, 'number': 119}  | {'precision': 0.4605263157894737, 'recall': 0.5258215962441315, 'f1': 0.49101271372205174, 'number': 1065}   | 0.3866            | 0.4807         | 0.4285     | 0.5679           |
+| 0.8884        | 14.0  | 70   | 1.1097          | {'precision': 0.31260364842454397, 'recall': 0.46600741656365885, 'f1': 0.37419354838709684, 'number': 809}    | {'precision': 0.29333333333333333, 'recall': 0.18487394957983194, 'f1': 0.2268041237113402, 'number': 119}  | {'precision': 0.4597791798107255, 'recall': 0.5474178403755868, 'f1': 0.4997856836690956, 'number': 1065}    | 0.3852            | 0.4927         | 0.4324     | 0.5710           |
+| 0.8759        | 15.0  | 75   | 1.0844          | {'precision': 0.3143100511073254, 'recall': 0.4561186650185414, 'f1': 0.3721633888048412, 'number': 809}       | {'precision': 0.275, 'recall': 0.18487394957983194, 'f1': 0.22110552763819097, 'number': 119}               | {'precision': 0.44804716285924834, 'recall': 0.5708920187793427, 'f1': 0.5020644095788603, 'number': 1065}   | 0.3826            | 0.5013         | 0.4340     | 0.5793           |
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/layoutlm-base-uncased",
+  "architectures": [
+    "LayoutLMForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-HEADER",
+    "2": "I-HEADER",
+    "3": "B-QUESTION",
+    "4": "I-QUESTION",
+    "5": "B-ANSWER",
+    "6": "I-ANSWER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANSWER": 5,
+    "B-HEADER": 1,
+    "B-QUESTION": 3,
+    "I-ANSWER": 6,
+    "I-HEADER": 2,
+    "I-QUESTION": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 512,
+  "model_type": "layoutlm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

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": ""
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e900a711707a090d4d8ed042a8c9002f840b888eb7aa3ee4b8e6ad2135ebe3
+size 450603969

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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c171eb48151a6f712517bf002dd7d43be136c8408d649c4ae7c8a23f1af5d84c
+size 4091