Hugging Face's logo

jaeger1
/
layoutlm-funsd

Token Classification
Transformers
PyTorch
TensorBoard
layoutlm
Generated from Trainer
Model card Files
xet
 Metrics Community
1
jaeger1 commited on
Commit
52e4763
·
1 Parent(s): e13a66c

End of training

Browse files
Files changed (4) hide show
  1. README.md +25 -25
  2. logs/events.out.tfevents.1685641948.kimv.12176.4 +2 -2
  3. pytorch_model.bin +1 -1
  4. tokenizer.json +2 -16
README.md CHANGED
@@ -15,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.6866
19
- - Answer: {'precision': 0.7205720572057206, 'recall': 0.8096415327564895, 'f1': 0.7625145518044238, 'number': 809}
20
- - Header: {'precision': 0.3181818181818182, 'recall': 0.35294117647058826, 'f1': 0.3346613545816733, 'number': 119}
21
- - Question: {'precision': 0.7839506172839507, 'recall': 0.8347417840375587, 'f1': 0.8085493406093679, 'number': 1065}
22
- - Overall Precision: 0.7292
23
- - Overall Recall: 0.7958
24
- - Overall F1: 0.7610
25
- - Overall Accuracy: 0.8048
26
 
27
  ## Model description
28
 
@@ -52,23 +52,23 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
57
- | 1.8292 | 1.0 | 10 | 1.6076 | {'precision': 0.014943960149439602, 'recall': 0.014833127317676144, 'f1': 0.01488833746898263, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.2132564841498559, 'recall': 0.13896713615023473, 'f1': 0.16827743035815804, 'number': 1065} | 0.1069 | 0.0803 | 0.0917 | 0.3499 |
58
- | 1.4992 | 2.0 | 20 | 1.2649 | {'precision': 0.15553121577217963, 'recall': 0.17552533992583436, 'f1': 0.16492450638792103, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.45795107033639143, 'recall': 0.5624413145539906, 'f1': 0.5048461862621155, 'number': 1065} | 0.3336 | 0.3718 | 0.3517 | 0.5779 |
59
- | 1.127 | 3.0 | 30 | 0.9502 | {'precision': 0.4658981748318924, 'recall': 0.5995055624227441, 'f1': 0.5243243243243242, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.6047904191616766, 'recall': 0.6638497652582159, 'f1': 0.6329453894359892, 'number': 1065} | 0.5379 | 0.5981 | 0.5664 | 0.6835 |
60
- | 0.8468 | 4.0 | 40 | 0.8052 | {'precision': 0.5737240075614367, 'recall': 0.7503090234857849, 'f1': 0.6502410283877879, 'number': 809} | {'precision': 0.15, 'recall': 0.05042016806722689, 'f1': 0.07547169811320754, 'number': 119} | {'precision': 0.672231985940246, 'recall': 0.7183098591549296, 'f1': 0.6945074897866546, 'number': 1065} | 0.6163 | 0.6914 | 0.6517 | 0.7343 |
61
- | 0.706 | 5.0 | 50 | 0.7191 | {'precision': 0.6361655773420479, 'recall': 0.7218788627935723, 'f1': 0.6763173132599883, 'number': 809} | {'precision': 0.18055555555555555, 'recall': 0.1092436974789916, 'f1': 0.13612565445026178, 'number': 119} | {'precision': 0.6922435362802335, 'recall': 0.7793427230046949, 'f1': 0.7332155477031801, 'number': 1065} | 0.6519 | 0.7160 | 0.6824 | 0.7683 |
62
- | 0.5832 | 6.0 | 60 | 0.6846 | {'precision': 0.6547231270358306, 'recall': 0.7453646477132262, 'f1': 0.6971098265895953, 'number': 809} | {'precision': 0.21951219512195122, 'recall': 0.15126050420168066, 'f1': 0.1791044776119403, 'number': 119} | {'precision': 0.6936866718628215, 'recall': 0.8356807511737089, 'f1': 0.75809199318569, 'number': 1065} | 0.6610 | 0.7582 | 0.7062 | 0.7898 |
63
- | 0.5197 | 7.0 | 70 | 0.6586 | {'precision': 0.6821621621621622, 'recall': 0.7799752781211372, 'f1': 0.7277970011534025, 'number': 809} | {'precision': 0.23469387755102042, 'recall': 0.19327731092436976, 'f1': 0.2119815668202765, 'number': 119} | {'precision': 0.7302363488182559, 'recall': 0.8413145539906103, 'f1': 0.7818499127399652, 'number': 1065} | 0.6889 | 0.7777 | 0.7306 | 0.7931 |
64
- | 0.4622 | 8.0 | 80 | 0.6479 | {'precision': 0.6830601092896175, 'recall': 0.7725587144622992, 'f1': 0.7250580046403712, 'number': 809} | {'precision': 0.2540983606557377, 'recall': 0.2605042016806723, 'f1': 0.2572614107883818, 'number': 119} | {'precision': 0.7464553794829024, 'recall': 0.8403755868544601, 'f1': 0.7906360424028268, 'number': 1065} | 0.6936 | 0.7782 | 0.7335 | 0.7983 |
65
- | 0.4162 | 9.0 | 90 | 0.6500 | {'precision': 0.6911447084233261, 'recall': 0.7911001236093943, 'f1': 0.7377521613832853, 'number': 809} | {'precision': 0.3008130081300813, 'recall': 0.31092436974789917, 'f1': 0.3057851239669422, 'number': 119} | {'precision': 0.7659574468085106, 'recall': 0.8450704225352113, 'f1': 0.8035714285714286, 'number': 1065} | 0.7091 | 0.7913 | 0.7479 | 0.8010 |
66
- | 0.3644 | 10.0 | 100 | 0.6503 | {'precision': 0.7041484716157205, 'recall': 0.7972805933250927, 'f1': 0.7478260869565218, 'number': 809} | {'precision': 0.3247863247863248, 'recall': 0.31932773109243695, 'f1': 0.3220338983050848, 'number': 119} | {'precision': 0.7757885763000852, 'recall': 0.8544600938967136, 'f1': 0.8132260947274352, 'number': 1065} | 0.7221 | 0.7993 | 0.7588 | 0.8078 |
67
- | 0.3255 | 11.0 | 110 | 0.6716 | {'precision': 0.7108953613807982, 'recall': 0.8145859085290482, 'f1': 0.7592165898617511, 'number': 809} | {'precision': 0.3333333333333333, 'recall': 0.3277310924369748, 'f1': 0.3305084745762712, 'number': 119} | {'precision': 0.7852112676056338, 'recall': 0.8375586854460094, 'f1': 0.8105406633348478, 'number': 1065} | 0.7294 | 0.7978 | 0.7620 | 0.8026 |
68
- | 0.3154 | 12.0 | 120 | 0.6760 | {'precision': 0.7207505518763797, 'recall': 0.8071693448702101, 'f1': 0.7615160349854228, 'number': 809} | {'precision': 0.3140495867768595, 'recall': 0.31932773109243695, 'f1': 0.31666666666666665, 'number': 119} | {'precision': 0.7812773403324584, 'recall': 0.8384976525821596, 'f1': 0.8088768115942028, 'number': 1065} | 0.7300 | 0.7948 | 0.7610 | 0.8039 |
69
- | 0.2872 | 13.0 | 130 | 0.6777 | {'precision': 0.7232635060639471, 'recall': 0.8108776266996292, 'f1': 0.7645687645687645, 'number': 809} | {'precision': 0.31451612903225806, 'recall': 0.3277310924369748, 'f1': 0.32098765432098764, 'number': 119} | {'precision': 0.7841601392515231, 'recall': 0.8460093896713615, 'f1': 0.8139114724480578, 'number': 1065} | 0.7321 | 0.8008 | 0.7649 | 0.8055 |
70
- | 0.2775 | 14.0 | 140 | 0.6824 | {'precision': 0.7250821467688937, 'recall': 0.8182941903584673, 'f1': 0.7688734030197445, 'number': 809} | {'precision': 0.31007751937984496, 'recall': 0.33613445378151263, 'f1': 0.3225806451612903, 'number': 119} | {'precision': 0.7839506172839507, 'recall': 0.8347417840375587, 'f1': 0.8085493406093679, 'number': 1065} | 0.7312 | 0.7983 | 0.7633 | 0.8048 |
71
- | 0.2744 | 15.0 | 150 | 0.6866 | {'precision': 0.7205720572057206, 'recall': 0.8096415327564895, 'f1': 0.7625145518044238, 'number': 809} | {'precision': 0.3181818181818182, 'recall': 0.35294117647058826, 'f1': 0.3346613545816733, 'number': 119} | {'precision': 0.7839506172839507, 'recall': 0.8347417840375587, 'f1': 0.8085493406093679, 'number': 1065} | 0.7292 | 0.7958 | 0.7610 | 0.8048 |
72
 
73
 
74
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the funsd dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.6975
19
+ - Answer: {'precision': 0.7111834961997828, 'recall': 0.8096415327564895, 'f1': 0.7572254335260116, 'number': 809}
20
+ - Header: {'precision': 0.3046875, 'recall': 0.3277310924369748, 'f1': 0.31578947368421056, 'number': 119}
21
+ - Question: {'precision': 0.7682819383259912, 'recall': 0.8187793427230047, 'f1': 0.7927272727272727, 'number': 1065}
22
+ - Overall Precision: 0.7170
23
+ - Overall Recall: 0.7858
24
+ - Overall F1: 0.7498
25
+ - Overall Accuracy: 0.8006
26
 
27
  ## Model description
28
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
57
+ | 1.8205 | 1.0 | 10 | 1.6197 | {'precision': 0.018433179723502304, 'recall': 0.019777503090234856, 'f1': 0.019081693500298154, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.20243362831858408, 'recall': 0.17183098591549295, 'f1': 0.18588115794819704, 'number': 1065} | 0.1123 | 0.0998 | 0.1057 | 0.3687 |
58
+ | 1.4872 | 2.0 | 20 | 1.2615 | {'precision': 0.11558441558441558, 'recall': 0.1100123609394314, 'f1': 0.11272957568081064, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.4534979423868313, 'recall': 0.5173708920187794, 'f1': 0.48333333333333334, 'number': 1065} | 0.3223 | 0.3211 | 0.3217 | 0.5529 |
59
+ | 1.1097 | 3.0 | 30 | 0.9582 | {'precision': 0.45864661654135336, 'recall': 0.45241038318912236, 'f1': 0.4555071561916615, 'number': 809} | {'precision': 0.08823529411764706, 'recall': 0.025210084033613446, 'f1': 0.039215686274509796, 'number': 119} | {'precision': 0.6037234042553191, 'recall': 0.6394366197183099, 'f1': 0.6210670314637483, 'number': 1065} | 0.5357 | 0.5268 | 0.5312 | 0.6937 |
60
+ | 0.8429 | 4.0 | 40 | 0.7753 | {'precision': 0.6193353474320241, 'recall': 0.7601977750309024, 'f1': 0.6825749167591565, 'number': 809} | {'precision': 0.2553191489361702, 'recall': 0.10084033613445378, 'f1': 0.14457831325301204, 'number': 119} | {'precision': 0.6663701067615658, 'recall': 0.7032863849765258, 'f1': 0.6843307446322522, 'number': 1065} | 0.6359 | 0.6904 | 0.6620 | 0.7557 |
61
+ | 0.6833 | 5.0 | 50 | 0.7026 | {'precision': 0.6558441558441559, 'recall': 0.7490729295426453, 'f1': 0.6993652625504905, 'number': 809} | {'precision': 0.3064516129032258, 'recall': 0.15966386554621848, 'f1': 0.20994475138121546, 'number': 119} | {'precision': 0.7068376068376069, 'recall': 0.7765258215962442, 'f1': 0.7400447427293065, 'number': 1065} | 0.6735 | 0.7285 | 0.6999 | 0.7858 |
62
+ | 0.5554 | 6.0 | 60 | 0.6718 | {'precision': 0.6733403582718651, 'recall': 0.7898640296662547, 'f1': 0.726962457337884, 'number': 809} | {'precision': 0.29411764705882354, 'recall': 0.16806722689075632, 'f1': 0.21390374331550802, 'number': 119} | {'precision': 0.7259816207184628, 'recall': 0.815962441314554, 'f1': 0.7683465959328029, 'number': 1065} | 0.6902 | 0.7667 | 0.7264 | 0.7943 |
63
+ | 0.4934 | 7.0 | 70 | 0.6565 | {'precision': 0.6820566631689402, 'recall': 0.8034610630407911, 'f1': 0.7377979568671965, 'number': 809} | {'precision': 0.2826086956521739, 'recall': 0.2184873949579832, 'f1': 0.24644549763033172, 'number': 119} | {'precision': 0.7274247491638796, 'recall': 0.8169014084507042, 'f1': 0.7695709862892524, 'number': 1065} | 0.6899 | 0.7757 | 0.7303 | 0.7962 |
64
+ | 0.4473 | 8.0 | 80 | 0.6501 | {'precision': 0.6903719912472648, 'recall': 0.7799752781211372, 'f1': 0.7324434126523505, 'number': 809} | {'precision': 0.2653061224489796, 'recall': 0.2184873949579832, 'f1': 0.23963133640552997, 'number': 119} | {'precision': 0.7345731191885038, 'recall': 0.815962441314554, 'f1': 0.7731316725978647, 'number': 1065} | 0.6952 | 0.7657 | 0.7287 | 0.8047 |
65
+ | 0.3997 | 9.0 | 90 | 0.6500 | {'precision': 0.7120708748615725, 'recall': 0.7948084054388134, 'f1': 0.7511682242990654, 'number': 809} | {'precision': 0.2608695652173913, 'recall': 0.25210084033613445, 'f1': 0.2564102564102564, 'number': 119} | {'precision': 0.7440068493150684, 'recall': 0.815962441314554, 'f1': 0.7783251231527093, 'number': 1065} | 0.7054 | 0.7737 | 0.7380 | 0.8078 |
66
+ | 0.3553 | 10.0 | 100 | 0.6592 | {'precision': 0.7158351409978309, 'recall': 0.8158220024721878, 'f1': 0.7625649913344889, 'number': 809} | {'precision': 0.3148148148148148, 'recall': 0.2857142857142857, 'f1': 0.29955947136563876, 'number': 119} | {'precision': 0.7599653379549394, 'recall': 0.8234741784037559, 'f1': 0.790446146913024, 'number': 1065} | 0.7193 | 0.7883 | 0.7522 | 0.8078 |
67
+ | 0.3215 | 11.0 | 110 | 0.6783 | {'precision': 0.701063829787234, 'recall': 0.8145859085290482, 'f1': 0.7535734705546027, 'number': 809} | {'precision': 0.29914529914529914, 'recall': 0.29411764705882354, 'f1': 0.29661016949152547, 'number': 119} | {'precision': 0.7712014134275619, 'recall': 0.819718309859155, 'f1': 0.7947200728265817, 'number': 1065} | 0.7159 | 0.7863 | 0.7494 | 0.8034 |
68
+ | 0.3131 | 12.0 | 120 | 0.6804 | {'precision': 0.7120879120879121, 'recall': 0.8009888751545118, 'f1': 0.7539267015706805, 'number': 809} | {'precision': 0.3125, 'recall': 0.29411764705882354, 'f1': 0.30303030303030304, 'number': 119} | {'precision': 0.7834224598930482, 'recall': 0.8253521126760563, 'f1': 0.8038408779149521, 'number': 1065} | 0.7285 | 0.7837 | 0.7551 | 0.8076 |
69
+ | 0.2891 | 13.0 | 130 | 0.6889 | {'precision': 0.7045454545454546, 'recall': 0.8046971569839307, 'f1': 0.7512983266012695, 'number': 809} | {'precision': 0.3135593220338983, 'recall': 0.31092436974789917, 'f1': 0.31223628691983124, 'number': 119} | {'precision': 0.7616580310880829, 'recall': 0.828169014084507, 'f1': 0.7935222672064778, 'number': 1065} | 0.7136 | 0.7878 | 0.7489 | 0.8034 |
70
+ | 0.2819 | 14.0 | 140 | 0.6979 | {'precision': 0.7063236870310825, 'recall': 0.8145859085290482, 'f1': 0.7566016073478761, 'number': 809} | {'precision': 0.3023255813953488, 'recall': 0.3277310924369748, 'f1': 0.314516129032258, 'number': 119} | {'precision': 0.7682819383259912, 'recall': 0.8187793427230047, 'f1': 0.7927272727272727, 'number': 1065} | 0.7146 | 0.7878 | 0.7494 | 0.8001 |
71
+ | 0.2779 | 15.0 | 150 | 0.6975 | {'precision': 0.7111834961997828, 'recall': 0.8096415327564895, 'f1': 0.7572254335260116, 'number': 809} | {'precision': 0.3046875, 'recall': 0.3277310924369748, 'f1': 0.31578947368421056, 'number': 119} | {'precision': 0.7682819383259912, 'recall': 0.8187793427230047, 'f1': 0.7927272727272727, 'number': 1065} | 0.7170 | 0.7858 | 0.7498 | 0.8006 |
72
 
73
 
74
  ### Framework versions
logs/events.out.tfevents.1685641948.kimv.12176.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb0a5883e9c986938f9083feb29a8887bb2aa0821be7a573fa32f68df98d62ee
3
- size 4918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15f7b2981f84df33df993a7fe00b16ff64501647d48291c334dea537e4393d6
3
+ size 14394
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d956c7111ef00d62d631f95be669515803b7d79e8f235b7de05d60936f9e5724
3
  size 450608389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b78339953da79d6bdd30a4ab06f897cf92b530468cd092236f2fba6c1aa024
3
  size 450608389
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 0,
16
- "pad_type_id": 0,
17
- "pad_token": "[PAD]"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,