End of training

README.md

@@ -0,0 +1,79 @@
+---
+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: 0.6889
+- Answer: {'precision': 0.697928026172301, 'recall': 0.7911001236093943, 'f1': 0.7415990730011587, 'number': 809}
+- Header: {'precision': 0.37272727272727274, 'recall': 0.3445378151260504, 'f1': 0.35807860262008734, 'number': 119}
+- Question: {'precision': 0.7824529991047449, 'recall': 0.8206572769953052, 'f1': 0.8010999083409717, 'number': 1065}
+- Overall Precision: 0.7253
+- Overall Recall: 0.7802
+- Overall F1: 0.7518
+- Overall Accuracy: 0.8070
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 1.8003        | 1.0   | 10   | 1.6003          | {'precision': 0.027941176470588237, 'recall': 0.023485784919653894, 'f1': 0.02552048354600403, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.2628120893561104, 'recall': 0.18779342723004694, 'f1': 0.2190580503833516, 'number': 1065} | 0.1520            | 0.1099         | 0.1275     | 0.3543           |
+| 1.458         | 2.0   | 20   | 1.2190          | {'precision': 0.15822002472187885, 'recall': 0.15822002472187885, 'f1': 0.15822002472187885, 'number': 809}   | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}                                                 | {'precision': 0.42168674698795183, 'recall': 0.5586854460093896, 'f1': 0.4806138933764136, 'number': 1065} | 0.3257            | 0.3628         | 0.3432     | 0.5974           |
+| 1.1074        | 3.0   | 30   | 0.9545          | {'precision': 0.4604486422668241, 'recall': 0.4820766378244747, 'f1': 0.47101449275362317, 'number': 809}     | {'precision': 0.26666666666666666, 'recall': 0.06722689075630252, 'f1': 0.10738255033557047, 'number': 119} | {'precision': 0.6383763837638377, 'recall': 0.6497652582159624, 'f1': 0.6440204746393672, 'number': 1065}  | 0.5558            | 0.5469         | 0.5513     | 0.7018           |
+| 0.8568        | 4.0   | 40   | 0.7809          | {'precision': 0.6104190260475651, 'recall': 0.6662546353522868, 'f1': 0.6371158392434988, 'number': 809}      | {'precision': 0.24074074074074073, 'recall': 0.1092436974789916, 'f1': 0.15028901734104044, 'number': 119}  | {'precision': 0.6952983725135624, 'recall': 0.7220657276995305, 'f1': 0.7084292952556425, 'number': 1065}  | 0.6466            | 0.6628         | 0.6546     | 0.7524           |
+| 0.6856        | 5.0   | 50   | 0.7109          | {'precision': 0.6309887869520897, 'recall': 0.765142150803461, 'f1': 0.6916201117318436, 'number': 809}       | {'precision': 0.25287356321839083, 'recall': 0.18487394957983194, 'f1': 0.21359223300970878, 'number': 119} | {'precision': 0.7244525547445255, 'recall': 0.7455399061032864, 'f1': 0.7348449791763073, 'number': 1065}  | 0.6631            | 0.7200         | 0.6904     | 0.7755           |
+| 0.5661        | 6.0   | 60   | 0.6759          | {'precision': 0.6450939457202505, 'recall': 0.7639060568603214, 'f1': 0.699490662139219, 'number': 809}       | {'precision': 0.3037974683544304, 'recall': 0.20168067226890757, 'f1': 0.24242424242424243, 'number': 119}  | {'precision': 0.7172995780590717, 'recall': 0.7981220657276995, 'f1': 0.7555555555555554, 'number': 1065}  | 0.6715            | 0.7486         | 0.7079     | 0.7957           |
+| 0.4904        | 7.0   | 70   | 0.6680          | {'precision': 0.6447916666666667, 'recall': 0.765142150803461, 'f1': 0.6998304126625212, 'number': 809}       | {'precision': 0.2542372881355932, 'recall': 0.25210084033613445, 'f1': 0.25316455696202533, 'number': 119}  | {'precision': 0.7282229965156795, 'recall': 0.7849765258215963, 'f1': 0.75553547220967, 'number': 1065}    | 0.6671            | 0.7451         | 0.7040     | 0.7994           |
+| 0.4429        | 8.0   | 80   | 0.6522          | {'precision': 0.6794462193823216, 'recall': 0.788627935723115, 'f1': 0.7299771167048056, 'number': 809}       | {'precision': 0.2894736842105263, 'recall': 0.2773109243697479, 'f1': 0.2832618025751073, 'number': 119}    | {'precision': 0.7532693984306887, 'recall': 0.8112676056338028, 'f1': 0.7811934900542497, 'number': 1065}  | 0.6977            | 0.7702         | 0.7322     | 0.8069           |
+| 0.3974        | 9.0   | 90   | 0.6525          | {'precision': 0.6832971800433839, 'recall': 0.7787391841779975, 'f1': 0.7279029462738301, 'number': 809}      | {'precision': 0.328, 'recall': 0.3445378151260504, 'f1': 0.33606557377049184, 'number': 119}                | {'precision': 0.7592267135325131, 'recall': 0.8112676056338028, 'f1': 0.7843849296413979, 'number': 1065}  | 0.7025            | 0.7702         | 0.7348     | 0.8061           |
+| 0.355         | 10.0  | 100  | 0.6603          | {'precision': 0.6900647948164147, 'recall': 0.7898640296662547, 'f1': 0.736599423631124, 'number': 809}       | {'precision': 0.3391304347826087, 'recall': 0.3277310924369748, 'f1': 0.3333333333333333, 'number': 119}    | {'precision': 0.7620297462817148, 'recall': 0.8178403755868544, 'f1': 0.788949275362319, 'number': 1065}   | 0.7092            | 0.7772         | 0.7417     | 0.8109           |
+| 0.3171        | 11.0  | 110  | 0.6769          | {'precision': 0.6833688699360341, 'recall': 0.792336217552534, 'f1': 0.733829421866056, 'number': 809}        | {'precision': 0.31746031746031744, 'recall': 0.33613445378151263, 'f1': 0.32653061224489793, 'number': 119} | {'precision': 0.7783832879200726, 'recall': 0.8046948356807512, 'f1': 0.791320406278855, 'number': 1065}   | 0.7104            | 0.7717         | 0.7398     | 0.8048           |
+| 0.3012        | 12.0  | 120  | 0.6808          | {'precision': 0.6913978494623656, 'recall': 0.7948084054388134, 'f1': 0.7395054629097183, 'number': 809}      | {'precision': 0.3584905660377358, 'recall': 0.31932773109243695, 'f1': 0.3377777777777778, 'number': 119}   | {'precision': 0.7787610619469026, 'recall': 0.8262910798122066, 'f1': 0.8018223234624146, 'number': 1065}  | 0.7207            | 0.7832         | 0.7507     | 0.8074           |
+| 0.2865        | 13.0  | 130  | 0.6882          | {'precision': 0.696604600219058, 'recall': 0.7861557478368356, 'f1': 0.7386759581881532, 'number': 809}       | {'precision': 0.3559322033898305, 'recall': 0.35294117647058826, 'f1': 0.35443037974683544, 'number': 119}  | {'precision': 0.7824909747292419, 'recall': 0.8140845070422535, 'f1': 0.7979751495628165, 'number': 1065}  | 0.7223            | 0.7752         | 0.7478     | 0.8057           |
+| 0.2728        | 14.0  | 140  | 0.6904          | {'precision': 0.697928026172301, 'recall': 0.7911001236093943, 'f1': 0.7415990730011587, 'number': 809}       | {'precision': 0.3761467889908257, 'recall': 0.3445378151260504, 'f1': 0.3596491228070175, 'number': 119}    | {'precision': 0.7856502242152467, 'recall': 0.8225352112676056, 'f1': 0.8036697247706422, 'number': 1065}  | 0.7272            | 0.7812         | 0.7533     | 0.8063           |
+| 0.2702        | 15.0  | 150  | 0.6889          | {'precision': 0.697928026172301, 'recall': 0.7911001236093943, 'f1': 0.7415990730011587, 'number': 809}       | {'precision': 0.37272727272727274, 'recall': 0.3445378151260504, 'f1': 0.35807860262008734, 'number': 119}  | {'precision': 0.7824529991047449, 'recall': 0.8206572769953052, 'f1': 0.8010999083409717, 'number': 1065}  | 0.7253            | 0.7802         | 0.7518     | 0.8070           |
+
+
+### Framework versions
+
+- Transformers 4.22.2
+- Pytorch 1.12.1+cu113
+- Datasets 2.5.2
+- Tokenizers 0.12.1

logs/events.out.tfevents.1665210610.01be1ea88f2b.182.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e3adc79055b469364546b311c258b98a107cc9f95b46b0671aed244e286592e
-size 4635
+oid sha256:91cd05356b556eb74e35ea896b86f9d686be71770d54f935bd1a82e5072bf1cf
+size 14111

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "apply_ocr": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv2FeatureExtractor",
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv2Processor",
+  "resample": 2,
+  "size": 224,
+  "tesseract_config": ""
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c498829dce7de4e1a2f5e66001db8e0c858c4e2a1c0ad29d7975ec5b742373e8
+oid sha256:a9a529182e83ec12b62a1d8f9a028ab0054d1db2dba095434d635bc658c40f8f
 size 450606565

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 +1,39 @@
+{
+  "additional_special_tokens": null,
+  "apply_ocr": false,
+  "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,
+  "name_or_path": "microsoft/layoutlmv2-base-uncased",
+  "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
+  ],
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "LayoutLMv2Tokenizer",
+  "unk_token": "[UNK]"
+}