Hugging Face's logo

sumitD
/
table-transformer-structure-recognition-v1.1-all-finetuned

Object Detection
Transformers
Safetensors
table-transformer
Generated from Trainer
Model card Files
xet
Community
sumitD commited on
Commit
6333bc4
·
verified ·
1 Parent(s): adb1b1c

sumitD/table-transformer-structure-recognition-v1.1-all-finetuned

Browse files
Files changed (3) hide show
  1. README.md +2 -44
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,33 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # table-transformer-structure-recognition-v1.1-all-finetuned
16
 
17
- This model is a fine-tuned version of [microsoft/table-transformer-structure-recognition-v1.1-all](https://huggingface.co/microsoft/table-transformer-structure-recognition-v1.1-all) on an unknown dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 2.7893
20
- - Map: 0.1665
21
- - Map 50: 0.3018
22
- - Map 75: 0.1319
23
- - Map Small: -1.0
24
- - Map Medium: -1.0
25
- - Map Large: 0.1666
26
- - Mar 1: 0.1636
27
- - Mar 10: 0.2261
28
- - Mar 100: 0.2754
29
- - Mar Small: -1.0
30
- - Mar Medium: -1.0
31
- - Mar Large: 0.2754
32
- - Map Table: 0.602
33
- - Mar 100 Table: 0.6
34
- - Map Table column: 0.0386
35
- - Mar 100 Table column: 0.1833
36
- - Map Table column header: 0.0026
37
- - Mar 100 Table column header: 0.1
38
- - Map Table projected row header: -1.0
39
- - Mar 100 Table projected row header: -1.0
40
- - Map Table row: 0.0228
41
- - Mar 100 Table row: 0.2182
42
- - Map Table spanning cell: -1.0
43
- - Mar 100 Table spanning cell: -1.0
44
 
45
  ## Model description
46
 
@@ -65,25 +39,9 @@ The following hyperparameters were used during training:
65
  - seed: 42
66
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
67
  - lr_scheduler_type: cosine
68
- - num_epochs: 10
69
  - mixed_precision_training: Native AMP
70
 
71
- ### Training results
72
-
73
- | Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Table | Mar 100 Table | Map Table column | Mar 100 Table column | Map Table column header | Mar 100 Table column header | Map Table projected row header | Mar 100 Table projected row header | Map Table row | Mar 100 Table row | Map Table spanning cell | Mar 100 Table spanning cell |
74
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:---------:|:-------------:|:----------------:|:--------------------:|:-----------------------:|:---------------------------:|:------------------------------:|:----------------------------------:|:-------------:|:-----------------:|:-----------------------:|:---------------------------:|
75
- | No log | 1.0 | 6 | 4.1052 | 0.1571 | 0.2968 | 0.1271 | -1.0 | -1.0 | 0.1585 | 0.15 | 0.1875 | 0.2625 | -1.0 | -1.0 | 0.2625 | 0.602 | 0.6 | 0.0154 | 0.1 | 0.0111 | 0.35 | -1.0 | -1.0 | 0.0 | 0.0 | -1.0 | -1.0 |
76
- | No log | 2.0 | 12 | 3.4755 | 0.1656 | 0.3162 | 0.1323 | -1.0 | -1.0 | 0.1673 | 0.15 | 0.2095 | 0.3064 | -1.0 | -1.0 | 0.3064 | 0.602 | 0.6 | 0.0194 | 0.1167 | 0.0292 | 0.4 | -1.0 | -1.0 | 0.0119 | 0.1091 | -1.0 | -1.0 |
77
- | No log | 3.0 | 18 | 3.2667 | 0.1649 | 0.339 | 0.1283 | -1.0 | -1.0 | 0.1659 | 0.1568 | 0.2098 | 0.317 | -1.0 | -1.0 | 0.317 | 0.602 | 0.6 | 0.0242 | 0.15 | 0.0145 | 0.4 | -1.0 | -1.0 | 0.0189 | 0.1182 | -1.0 | -1.0 |
78
- | No log | 4.0 | 24 | 3.1130 | 0.1629 | 0.3219 | 0.1269 | -1.0 | -1.0 | 0.1635 | 0.1591 | 0.1909 | 0.2841 | -1.0 | -1.0 | 0.2841 | 0.602 | 0.6 | 0.0263 | 0.15 | 0.0031 | 0.25 | -1.0 | -1.0 | 0.0201 | 0.1364 | -1.0 | -1.0 |
79
- | No log | 5.0 | 30 | 2.9493 | 0.1624 | 0.3019 | 0.1283 | -1.0 | -1.0 | 0.163 | 0.1591 | 0.1992 | 0.2958 | -1.0 | -1.0 | 0.2958 | 0.602 | 0.6 | 0.0271 | 0.1333 | 0.0033 | 0.25 | -1.0 | -1.0 | 0.017 | 0.2 | -1.0 | -1.0 |
80
- | No log | 6.0 | 36 | 2.9625 | 0.1645 | 0.3081 | 0.1281 | -1.0 | -1.0 | 0.1647 | 0.1614 | 0.2117 | 0.2879 | -1.0 | -1.0 | 0.2879 | 0.602 | 0.6 | 0.0319 | 0.1333 | 0.0042 | 0.2 | -1.0 | -1.0 | 0.0197 | 0.2182 | -1.0 | -1.0 |
81
- | No log | 7.0 | 42 | 2.8784 | 0.1653 | 0.3025 | 0.1282 | -1.0 | -1.0 | 0.1655 | 0.1614 | 0.2095 | 0.2898 | -1.0 | -1.0 | 0.2898 | 0.602 | 0.6 | 0.0345 | 0.15 | 0.0043 | 0.2 | -1.0 | -1.0 | 0.0203 | 0.2091 | -1.0 | -1.0 |
82
- | No log | 8.0 | 48 | 2.8191 | 0.1661 | 0.3019 | 0.1318 | -1.0 | -1.0 | 0.1663 | 0.1636 | 0.2345 | 0.2879 | -1.0 | -1.0 | 0.2879 | 0.602 | 0.6 | 0.0362 | 0.1833 | 0.0034 | 0.15 | -1.0 | -1.0 | 0.0228 | 0.2182 | -1.0 | -1.0 |
83
- | No log | 9.0 | 54 | 2.7933 | 0.1667 | 0.3018 | 0.1318 | -1.0 | -1.0 | 0.1668 | 0.1636 | 0.2386 | 0.2879 | -1.0 | -1.0 | 0.2879 | 0.602 | 0.6 | 0.0386 | 0.1833 | 0.0034 | 0.15 | -1.0 | -1.0 | 0.0227 | 0.2182 | -1.0 | -1.0 |
84
- | No log | 10.0 | 60 | 2.7893 | 0.1665 | 0.3018 | 0.1319 | -1.0 | -1.0 | 0.1666 | 0.1636 | 0.2261 | 0.2754 | -1.0 | -1.0 | 0.2754 | 0.602 | 0.6 | 0.0386 | 0.1833 | 0.0026 | 0.1 | -1.0 | -1.0 | 0.0228 | 0.2182 | -1.0 | -1.0 |
85
-
86
-
87
  ### Framework versions
88
 
89
  - Transformers 4.48.2
 
14
 
15
  # table-transformer-structure-recognition-v1.1-all-finetuned
16
 
17
+ This model is a fine-tuned version of [microsoft/table-transformer-structure-recognition-v1.1-all](https://huggingface.co/microsoft/table-transformer-structure-recognition-v1.1-all) on the None dataset.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: cosine
42
+ - num_epochs: 2
43
  - mixed_precision_training: Native AMP
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.48.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1343daa4dd0358e028470fc6880b0d920c8785fa78b292b3b6305a0e98c1566c
3
  size 115437156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ecc5ed44834ffcade7d7e3313dbdc6681b18a702c564f30dcdab35df7cf54eb
3
  size 115437156
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4be7958b802fc11c00f739d92ff277dfe3e2f3552d7c272e1fac0d44fe0d0362
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8872c657a3a555eaecb810e630e5e9342731a827e9850f57f27a42793d28b6cd
3
  size 5304