End of training

README.md

@@ -14,19 +14,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4071
-- Footer: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186}
-- Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373}
-- Able: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100}
-- Aption: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148}
-- Ext: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566}
-- Icture: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270}
-- Itle: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45}
-- Ootnote: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8}
-- Overall Precision: 0.0
-- Overall Recall: 0.0
-- Overall F1: 0.0
-- Overall Accuracy: 0.6399
+- Loss: 1.5413
+- Footer: {'precision': 0.9381835473133618, 'recall': 0.8653508771929824, 'f1': 0.9002966005019393, 'number': 2280}
+- Header: {'precision': 0.6690058479532164, 'recall': 0.601472134595163, 'f1': 0.6334440753045404, 'number': 951}
+- Able: {'precision': 0.19949254678084363, 'recall': 0.5143090760425184, 'f1': 0.2874771480804387, 'number': 1223}
+- Aption: {'precision': 0.32124352331606215, 'recall': 0.07515151515151515, 'f1': 0.12180746561886051, 'number': 825}
+- Ext: {'precision': 0.34080531340805315, 'recall': 0.4647608264930654, 'f1': 0.39324631780625074, 'number': 3533}
+- Icture: {'precision': 0.0546448087431694, 'recall': 0.13157894736842105, 'f1': 0.0772200772200772, 'number': 608}
+- Itle: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
+- Ootnote: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145}
+- Ormula: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360}
+- Overall Precision: 0.3939
+- Overall Recall: 0.4936
+- Overall F1: 0.4382
+- Overall Accuracy: 0.7180
 
 ## Model description
 
@@ -47,7 +48,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
 - train_batch_size: 2
-- eval_batch_size: 4
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,13 +56,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Footer                                                      | Header                                                      | Able                                                        | Aption                                                      | Ext                                                         | Icture                                                      | Itle                                                       | Ootnote                                                   | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:----------------------------------------------------------:|:---------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 1.1724        | 1.0   | 1950 | 1.4537          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
-| 1.2004        | 2.0   | 3900 | 1.4094          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
-| 1.2026        | 3.0   | 5850 | 1.4038          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
-| 1.2107        | 4.0   | 7800 | 1.4217          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
-| 1.1836        | 5.0   | 9750 | 1.4071          | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 186} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 373} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 100} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 148} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 566} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 270} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 45} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | 0.0               | 0.0            | 0.0        | 0.6399           |
+| Training Loss | Epoch | Step | Validation Loss | Footer                                                                                                    | Header                                                                                                   | Able                                                                                                        | Aption                                                                                                      | Ext                                                                                                         | Icture                                                                                                         | Itle                                                        | Ootnote                                                     | Ormula                                                      | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.4772        | 1.0   | 500  | 1.3891          | {'precision': 0.8112648221343873, 'recall': 0.7201754385964912, 'f1': 0.763011152416357, 'number': 2280}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 951}                                              | {'precision': 0.13366666666666666, 'recall': 0.32788225674570726, 'f1': 0.1899123845607388, 'number': 1223} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 825}                                                 | {'precision': 0.2245841035120148, 'recall': 0.27512029436739316, 'f1': 0.24729678157995166, 'number': 3533} | {'precision': 0.022222222222222223, 'recall': 0.008223684210526315, 'f1': 0.012004801920768306, 'number': 608} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3131            | 0.3007         | 0.3068     | 0.7042           |
+| 0.2598        | 2.0   | 1000 | 1.3046          | {'precision': 0.672650475184794, 'recall': 0.8381578947368421, 'f1': 0.7463386057410663, 'number': 2280}  | {'precision': 0.28655597214783074, 'recall': 0.562565720294427, 'f1': 0.3797019162526614, 'number': 951} | {'precision': 0.12042429284525791, 'recall': 0.473426001635323, 'f1': 0.19200795887912453, 'number': 1223}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 825}                                                 | {'precision': 0.22616279069767442, 'recall': 0.4404189074440985, 'f1': 0.29885719773360225, 'number': 3533} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 608}                                                    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.2682            | 0.4561         | 0.3378     | 0.6730           |
+| 0.1936        | 3.0   | 1500 | 1.4208          | {'precision': 0.9038104089219331, 'recall': 0.8530701754385965, 'f1': 0.8777075812274369, 'number': 2280} | {'precision': 0.6213468869123253, 'recall': 0.5141955835962145, 'f1': 0.5627157652474108, 'number': 951} | {'precision': 0.16486261448792672, 'recall': 0.4856909239574816, 'f1': 0.2461665975963531, 'number': 1223}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 825}                                                 | {'precision': 0.2463847702727439, 'recall': 0.3809793376733654, 'f1': 0.2992441084926634, 'number': 3533}   | {'precision': 0.02721774193548387, 'recall': 0.044407894736842105, 'f1': 0.03375, 'number': 608}               | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3385            | 0.4382         | 0.3819     | 0.7043           |
+| 0.1392        | 4.0   | 2000 | 1.7208          | {'precision': 0.9363636363636364, 'recall': 0.8583333333333333, 'f1': 0.8956521739130435, 'number': 2280} | {'precision': 0.6706521739130434, 'recall': 0.6487907465825447, 'f1': 0.6595403527525386, 'number': 951} | {'precision': 0.15699904122722916, 'recall': 0.53556827473426, 'f1': 0.24281742354031513, 'number': 1223}   | {'precision': 0.18992248062015504, 'recall': 0.059393939393939395, 'f1': 0.0904893813481071, 'number': 825} | {'precision': 0.2668534407284188, 'recall': 0.43136144919332015, 'f1': 0.3297273907399394, 'number': 3533}  | {'precision': 0.046700507614213196, 'recall': 0.0756578947368421, 'f1': 0.05775266792215945, 'number': 608}    | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3430            | 0.4827         | 0.4010     | 0.6703           |
+| 0.0899        | 5.0   | 2500 | 1.5413          | {'precision': 0.9381835473133618, 'recall': 0.8653508771929824, 'f1': 0.9002966005019393, 'number': 2280} | {'precision': 0.6690058479532164, 'recall': 0.601472134595163, 'f1': 0.6334440753045404, 'number': 951}  | {'precision': 0.19949254678084363, 'recall': 0.5143090760425184, 'f1': 0.2874771480804387, 'number': 1223}  | {'precision': 0.32124352331606215, 'recall': 0.07515151515151515, 'f1': 0.12180746561886051, 'number': 825} | {'precision': 0.34080531340805315, 'recall': 0.4647608264930654, 'f1': 0.39324631780625074, 'number': 3533} | {'precision': 0.0546448087431694, 'recall': 0.13157894736842105, 'f1': 0.0772200772200772, 'number': 608}      | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 145} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 360} | 0.3939            | 0.4936         | 0.4382     | 0.7180           |
 
 
 ### Framework versions

logs/events.out.tfevents.1679330367.138-2-233-57.342634.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e760dbdd0a19e1c020360a54ac6ac4f907ff2712741244854cdecf22a282e47e
-size 7919
+oid sha256:1686af6ac80511f569ba3626f01eae903c5baa94917bda0eab29a117e004deeb
+size 8273

preprocessor_config.json

@@ -1,24 +1,11 @@
 {
   "apply_ocr": false,
-  "do_normalize": true,
-  "do_rescale": true,
   "do_resize": true,
-  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "LayoutLMv3ImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
+  "feature_extractor_type": "LayoutLMv2FeatureExtractor",
+  "image_processor_type": "LayoutLMv2ImageProcessor",
   "ocr_lang": null,
-  "processor_class": "LayoutLMv3Processor",
+  "processor_class": "LayoutLMv2Processor",
   "resample": 2,
-  "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,
     "width": 224

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,56 +1,21 @@
 {
-  "add_prefix_space": true,
+  "additional_special_tokens": null,
   "apply_ocr": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
   "cls_token_box": [
     0,
     0,
     0,
     0
   ],
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "microsoft/layoutlmv3-base",
+  "name_or_path": "pmorelr/layoutlm-doclaynet-test",
+  "never_split": null,
   "only_label_first_subword": true,
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "[PAD]",
   "pad_token_box": [
     0,
     0,
@@ -58,30 +23,17 @@
     0
   ],
   "pad_token_label": -100,
-  "processor_class": "LayoutLMv3Processor",
-  "sep_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "processor_class": "LayoutLMv2Processor",
+  "sep_token": "[SEP]",
   "sep_token_box": [
-    0,
-    0,
-    0,
-    0
+    1000,
+    1000,
+    1000,
+    1000
   ],
   "special_tokens_map_file": null,
-  "tokenizer_class": "LayoutLMv3Tokenizer",
-  "trim_offsets": true,
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "LayoutLMv2Tokenizer",
+  "unk_token": "[UNK]"
 }