End of training

README.md

@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [moritzbur/lilt-GottBERT-base](https://huggingface.co/moritzbur/lilt-GottBERT-base) on the xfund dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0170
-- Answer: {'precision': 0.8059836808703535, 'recall': 0.8193548387096774, 'f1': 0.8126142595978061, 'number': 1085}
-- Header: {'precision': 0.6590909090909091, 'recall': 0.5, 'f1': 0.5686274509803921, 'number': 58}
-- Question: {'precision': 0.7037037037037037, 'recall': 0.837465564738292, 'f1': 0.7647798742138364, 'number': 726}
-- Overall Precision: 0.7588
-- Overall Recall: 0.8165
-- Overall F1: 0.7866
-- Overall Accuracy: 0.7433
+- Loss: 1.7402
+- Answer: {'precision': 0.7931914893617021, 'recall': 0.8589861751152074, 'f1': 0.8247787610619469, 'number': 1085}
+- Header: {'precision': 0.5581395348837209, 'recall': 0.41379310344827586, 'f1': 0.4752475247524752, 'number': 58}
+- Question: {'precision': 0.7877906976744186, 'recall': 0.7465564738292011, 'f1': 0.7666195190947666, 'number': 726}
+- Overall Precision: 0.7859
+- Overall Recall: 0.8015
+- Overall F1: 0.7936
+- Overall Accuracy: 0.7255
 
 ## Model description
 
@@ -44,30 +44,29 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 2500
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch    | Step | Validation Loss | Answer                                                                                                    | Header                                                                                                    | Question                                                                                                 | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:--------:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.6294        | 10.5263  | 200  | 1.2270          | {'precision': 0.7253032928942807, 'recall': 0.7714285714285715, 'f1': 0.7476552032157213, 'number': 1085} | {'precision': 0.4117647058823529, 'recall': 0.4827586206896552, 'f1': 0.4444444444444445, 'number': 58}   | {'precision': 0.6296728971962616, 'recall': 0.7424242424242424, 'f1': 0.6814159292035398, 'number': 726} | 0.6756            | 0.7512         | 0.7114     | 0.7180           |
-| 0.0376        | 21.0526  | 400  | 1.5753          | {'precision': 0.7734447539461468, 'recall': 0.7677419354838709, 'f1': 0.7705827937095282, 'number': 1085} | {'precision': 0.5, 'recall': 0.39655172413793105, 'f1': 0.4423076923076923, 'number': 58}                 | {'precision': 0.6336302895322939, 'recall': 0.7837465564738292, 'f1': 0.7007389162561576, 'number': 726} | 0.7051            | 0.7624         | 0.7326     | 0.7219           |
-| 0.0093        | 31.5789  | 600  | 1.7096          | {'precision': 0.8057971014492754, 'recall': 0.7686635944700461, 'f1': 0.7867924528301887, 'number': 1085} | {'precision': 0.4807692307692308, 'recall': 0.43103448275862066, 'f1': 0.45454545454545453, 'number': 58} | {'precision': 0.643702906350915, 'recall': 0.8236914600550964, 'f1': 0.7226586102719034, 'number': 726}  | 0.7227            | 0.7796         | 0.7501     | 0.7347           |
-| 0.0063        | 42.1053  | 800  | 2.0163          | {'precision': 0.760705289672544, 'recall': 0.8350230414746543, 'f1': 0.7961335676625658, 'number': 1085}  | {'precision': 0.55, 'recall': 0.3793103448275862, 'f1': 0.4489795918367347, 'number': 58}                 | {'precision': 0.698090692124105, 'recall': 0.8057851239669421, 'f1': 0.748081841432225, 'number': 726}   | 0.7313            | 0.8095         | 0.7684     | 0.7047           |
-| 0.0041        | 52.6316  | 1000 | 1.7820          | {'precision': 0.773403324584427, 'recall': 0.8147465437788018, 'f1': 0.793536804308797, 'number': 1085}   | {'precision': 0.627906976744186, 'recall': 0.46551724137931033, 'f1': 0.5346534653465347, 'number': 58}   | {'precision': 0.6758544652701213, 'recall': 0.8443526170798898, 'f1': 0.7507654623392529, 'number': 726} | 0.7281            | 0.8154         | 0.7693     | 0.7344           |
-| 0.0023        | 63.1579  | 1200 | 1.9631          | {'precision': 0.8218390804597702, 'recall': 0.7907834101382488, 'f1': 0.8060122123062471, 'number': 1085} | {'precision': 0.6444444444444445, 'recall': 0.5, 'f1': 0.5631067961165049, 'number': 58}                  | {'precision': 0.6841491841491841, 'recall': 0.8085399449035813, 'f1': 0.7411616161616162, 'number': 726} | 0.7571            | 0.7887         | 0.7725     | 0.7379           |
-| 0.0016        | 73.6842  | 1400 | 1.8911          | {'precision': 0.7939282428702852, 'recall': 0.7953917050691244, 'f1': 0.794659300184162, 'number': 1085}  | {'precision': 0.5909090909090909, 'recall': 0.4482758620689655, 'f1': 0.5098039215686274, 'number': 58}   | {'precision': 0.6629834254143646, 'recall': 0.8264462809917356, 'f1': 0.7357449417535254, 'number': 726} | 0.7313            | 0.7967         | 0.7626     | 0.7442           |
-| 0.0012        | 84.2105  | 1600 | 1.9599          | {'precision': 0.8111954459203036, 'recall': 0.7880184331797235, 'f1': 0.7994389901823281, 'number': 1085} | {'precision': 0.6666666666666666, 'recall': 0.41379310344827586, 'f1': 0.5106382978723404, 'number': 58}  | {'precision': 0.7020785219399538, 'recall': 0.837465564738292, 'f1': 0.7638190954773869, 'number': 726}  | 0.7602            | 0.7956         | 0.7775     | 0.7356           |
-| 0.0006        | 94.7368  | 1800 | 2.1117          | {'precision': 0.8485772357723578, 'recall': 0.7695852534562212, 'f1': 0.8071532141130981, 'number': 1085} | {'precision': 0.6444444444444445, 'recall': 0.5, 'f1': 0.5631067961165049, 'number': 58}                  | {'precision': 0.7149817295980512, 'recall': 0.8085399449035813, 'f1': 0.7588881706528765, 'number': 726} | 0.7843            | 0.7764         | 0.7803     | 0.7377           |
-| 0.0006        | 105.2632 | 2000 | 2.0033          | {'precision': 0.8036866359447005, 'recall': 0.8036866359447005, 'f1': 0.8036866359447006, 'number': 1085} | {'precision': 0.6410256410256411, 'recall': 0.43103448275862066, 'f1': 0.5154639175257731, 'number': 58}  | {'precision': 0.6780973451327433, 'recall': 0.8443526170798898, 'f1': 0.7521472392638038, 'number': 726} | 0.7446            | 0.8079         | 0.7750     | 0.7409           |
-| 0.0003        | 115.7895 | 2200 | 2.0170          | {'precision': 0.8059836808703535, 'recall': 0.8193548387096774, 'f1': 0.8126142595978061, 'number': 1085} | {'precision': 0.6590909090909091, 'recall': 0.5, 'f1': 0.5686274509803921, 'number': 58}                  | {'precision': 0.7037037037037037, 'recall': 0.837465564738292, 'f1': 0.7647798742138364, 'number': 726}  | 0.7588            | 0.8165         | 0.7866     | 0.7433           |
-| 0.0003        | 126.3158 | 2400 | 2.0173          | {'precision': 0.8104761904761905, 'recall': 0.784331797235023, 'f1': 0.7971896955503512, 'number': 1085}  | {'precision': 0.6363636363636364, 'recall': 0.4827586206896552, 'f1': 0.5490196078431373, 'number': 58}   | {'precision': 0.7096018735362998, 'recall': 0.8347107438016529, 'f1': 0.7670886075949367, 'number': 726} | 0.7623            | 0.7945         | 0.7781     | 0.7393           |
+| Training Loss | Epoch | Step | Validation Loss | Answer                                                                                                    | Header                                                                                                    | Question                                                                                                 | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.0373        | 20.0  | 200  | 1.8211          | {'precision': 0.7350565428109854, 'recall': 0.8387096774193549, 'f1': 0.7834696513129574, 'number': 1085} | {'precision': 0.5135135135135135, 'recall': 0.3275862068965517, 'f1': 0.4, 'number': 58}                  | {'precision': 0.7130102040816326, 'recall': 0.7699724517906336, 'f1': 0.7403973509933776, 'number': 726} | 0.7227            | 0.7961         | 0.7576     | 0.7076           |
+| 0.0345        | 40.0  | 400  | 2.1454          | {'precision': 0.7412698412698413, 'recall': 0.8608294930875576, 'f1': 0.796588486140725, 'number': 1085}  | {'precision': 0.48148148148148145, 'recall': 0.4482758620689655, 'f1': 0.4642857142857143, 'number': 58}  | {'precision': 0.6554809843400448, 'recall': 0.8071625344352618, 'f1': 0.7234567901234568, 'number': 726} | 0.7002            | 0.8272         | 0.7584     | 0.6866           |
+| 0.0114        | 60.0  | 600  | 2.0185          | {'precision': 0.8492723492723493, 'recall': 0.7529953917050691, 'f1': 0.7982413287738153, 'number': 1085} | {'precision': 0.7857142857142857, 'recall': 0.3793103448275862, 'f1': 0.5116279069767441, 'number': 58}   | {'precision': 0.7317073170731707, 'recall': 0.7851239669421488, 'f1': 0.7574750830564784, 'number': 726} | 0.7965            | 0.7539         | 0.7746     | 0.7294           |
+| 0.0043        | 80.0  | 800  | 1.7402          | {'precision': 0.7931914893617021, 'recall': 0.8589861751152074, 'f1': 0.8247787610619469, 'number': 1085} | {'precision': 0.5581395348837209, 'recall': 0.41379310344827586, 'f1': 0.4752475247524752, 'number': 58}  | {'precision': 0.7877906976744186, 'recall': 0.7465564738292011, 'f1': 0.7666195190947666, 'number': 726} | 0.7859            | 0.8015         | 0.7936     | 0.7255           |
+| 0.0013        | 100.0 | 1000 | 1.8975          | {'precision': 0.8072727272727273, 'recall': 0.8184331797235023, 'f1': 0.8128146453089244, 'number': 1085} | {'precision': 0.5, 'recall': 0.41379310344827586, 'f1': 0.4528301886792453, 'number': 58}                 | {'precision': 0.7246022031823746, 'recall': 0.8154269972451791, 'f1': 0.7673363577446531, 'number': 726} | 0.7654            | 0.8047         | 0.7846     | 0.7248           |
+| 0.0009        | 120.0 | 1200 | 1.8875          | {'precision': 0.8050314465408805, 'recall': 0.8258064516129032, 'f1': 0.8152866242038216, 'number': 1085} | {'precision': 0.6666666666666666, 'recall': 0.3793103448275862, 'f1': 0.48351648351648346, 'number': 58}  | {'precision': 0.7094017094017094, 'recall': 0.800275482093664, 'f1': 0.7521035598705502, 'number': 726}  | 0.7628            | 0.8020         | 0.7820     | 0.7334           |
+| 0.0003        | 140.0 | 1400 | 1.9918          | {'precision': 0.8246575342465754, 'recall': 0.832258064516129, 'f1': 0.8284403669724771, 'number': 1085}  | {'precision': 0.4716981132075472, 'recall': 0.43103448275862066, 'f1': 0.45045045045045046, 'number': 58} | {'precision': 0.7354430379746836, 'recall': 0.800275482093664, 'f1': 0.766490765171504, 'number': 726}   | 0.7786            | 0.8074         | 0.7928     | 0.7316           |
+| 0.0003        | 160.0 | 1600 | 2.4537          | {'precision': 0.7632850241545893, 'recall': 0.8737327188940092, 'f1': 0.8147829823807479, 'number': 1085} | {'precision': 0.6857142857142857, 'recall': 0.41379310344827586, 'f1': 0.5161290322580646, 'number': 58}  | {'precision': 0.7536231884057971, 'recall': 0.7878787878787878, 'f1': 0.7703703703703704, 'number': 726} | 0.7583            | 0.8261         | 0.7908     | 0.6903           |
+| 0.0004        | 180.0 | 1800 | 2.1619          | {'precision': 0.785593220338983, 'recall': 0.8543778801843318, 'f1': 0.8185430463576159, 'number': 1085}  | {'precision': 0.5641025641025641, 'recall': 0.3793103448275862, 'f1': 0.4536082474226804, 'number': 58}   | {'precision': 0.7718579234972678, 'recall': 0.778236914600551, 'f1': 0.7750342935528121, 'number': 726}  | 0.7760            | 0.8101         | 0.7927     | 0.7197           |
+| 0.0003        | 200.0 | 2000 | 2.1507          | {'precision': 0.7948051948051948, 'recall': 0.8460829493087557, 'f1': 0.8196428571428571, 'number': 1085} | {'precision': 0.631578947368421, 'recall': 0.41379310344827586, 'f1': 0.5, 'number': 58}                  | {'precision': 0.7438551099611902, 'recall': 0.7920110192837465, 'f1': 0.7671781187458305, 'number': 726} | 0.7716            | 0.8117         | 0.7911     | 0.7207           |
 
 
 ### Framework versions

logs/events.out.tfevents.1732498300.d522202133e6.30.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b686c850bfe426995d1809f6c5872a791061a77413be071fa5502203111953d3
-size 11848
+oid sha256:66ac6958864dadae325bc2f9701926ea5f227970d86c47ae96645e868faba80e
+size 12917

logs/events.out.tfevents.1732500998.d522202133e6.30.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c228651936a1fe66c0aa7679c4ea6990e71fb56f3cbc31766fb67ab26522b5dc
+size 592

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4a4954dbca90fb4278ff42eac6baba8595cc3342970e6c3b134f032c3b39e0
+oid sha256:eece7cce835b87bd18a555f9df109225ae609d6039ab8cd9edf5dbaaefc7efae
 size 526085132

preprocessor_config.json

@@ -8,7 +8,7 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "LayoutLMv3FeatureExtractor",
+  "image_processor_type": "LayoutLMv3ImageProcessor",
   "image_std": [
     0.5,
     0.5,

tokenizer_config.json

@@ -54,8 +54,10 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 512,
   "only_label_first_subword": true,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
   "pad_token_box": [
     0,
@@ -64,6 +66,8 @@
     0
   ],
   "pad_token_label": -100,
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "processor_class": "LayoutLMv3Processor",
   "sep_token": "</s>",
   "sep_token_box": [
@@ -72,7 +76,10 @@
     0,
     0
   ],
+  "stride": 0,
   "tokenizer_class": "LayoutLMv3Tokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }