Hugging Face's logo

YufeiWeng
/
donut-base-beans

Image Classification
Transformers
Safetensors
beit
vision
Generated from Trainer
Model card Files
xet
Community
YufeiWeng commited on
Commit
432bcf9
·
verified ·
1 Parent(s): bc32807

Model save

Browse files
Files changed (3) hide show
  1. README.md +50 -12
  2. p_object.json +0 -0
  3. prediction_reference.json +0 -0
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - F1: 0.9705
20
- - Loss: 0.0391
21
 
22
  ## Model description
23
 
@@ -37,22 +37,60 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 3e-05
40
- - train_batch_size: 128
41
- - eval_batch_size: 128
42
  - seed: 1337
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 5.0
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | F1 | Validation Loss |
50
- |:-------------:|:-----:|:----:|:------:|:---------------:|
51
- | 0.0594 | 1.0 | 1981 | 0.9705 | 0.0440 |
52
- | 0.0678 | 2.0 | 3962 | 0.9705 | 0.0447 |
53
- | 0.0615 | 3.0 | 5943 | 0.9705 | 0.0416 |
54
- | 0.0685 | 4.0 | 7924 | 0.9705 | 0.0385 |
55
- | 0.0582 | 5.0 | 9905 | 0.9705 | 0.0391 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0478
20
+ - F1: 0.6048
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 3e-05
40
+ - train_batch_size: 64
41
+ - eval_batch_size: 64
42
  - seed: 1337
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - training_steps: 10000
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
50
+ |:-------------:|:------:|:----:|:---------------:|:------:|
51
+ | 0.1165 | 0.0126 | 50 | 0.0642 | 0.4177 |
52
+ | 0.0942 | 0.0252 | 100 | 0.0485 | 0.4772 |
53
+ | 0.1076 | 0.0379 | 150 | 0.0584 | 0.4643 |
54
+ | 0.1103 | 0.0505 | 200 | 0.0446 | nan |
55
+ | 0.0873 | 0.0631 | 250 | 0.0518 | 0.5313 |
56
+ | 0.1053 | 0.0757 | 300 | 0.0736 | 0.5329 |
57
+ | 0.0797 | 0.0884 | 350 | 0.0726 | 0.5326 |
58
+ | 0.0857 | 0.1010 | 400 | 0.0693 | 0.5498 |
59
+ | 0.0885 | 0.1136 | 450 | 0.0917 | nan |
60
+ | 0.102 | 0.1262 | 500 | 0.0580 | 0.5649 |
61
+ | 0.0716 | 0.1389 | 550 | 0.0797 | 0.5381 |
62
+ | 0.0854 | 0.1515 | 600 | 0.0744 | 0.5718 |
63
+ | 0.089 | 0.1641 | 650 | 0.0504 | 0.5790 |
64
+ | 0.0721 | 0.1767 | 700 | 0.0618 | 0.5727 |
65
+ | 0.0721 | 0.1893 | 750 | 0.0703 | 0.5904 |
66
+ | 0.0865 | 0.2020 | 800 | 0.0588 | 0.5953 |
67
+ | 0.0767 | 0.2146 | 850 | 0.0437 | 0.5918 |
68
+ | 0.0773 | 0.2272 | 900 | 0.0568 | 0.5957 |
69
+ | 0.0748 | 0.2398 | 950 | 0.0465 | 0.5942 |
70
+ | 0.0761 | 0.2525 | 1000 | 0.0660 | nan |
71
+ | 0.0855 | 0.2651 | 1050 | 0.0491 | 0.5964 |
72
+ | 0.0832 | 0.2777 | 1100 | 0.0498 | 0.6048 |
73
+ | 0.0821 | 0.2903 | 1150 | 0.0597 | 0.6032 |
74
+ | 0.0715 | 0.3030 | 1200 | 0.0643 | nan |
75
+ | 0.085 | 0.3156 | 1250 | 0.0659 | 0.6054 |
76
+ | 0.0826 | 0.3282 | 1300 | 0.0556 | 0.6012 |
77
+ | 0.064 | 0.3408 | 1350 | 0.0564 | nan |
78
+ | 0.0854 | 0.3534 | 1400 | 0.0552 | nan |
79
+ | 0.0702 | 0.3661 | 1450 | 0.0675 | 0.6061 |
80
+ | 0.0771 | 0.3787 | 1500 | 0.0578 | nan |
81
+ | 0.08 | 0.3913 | 1550 | 0.0492 | nan |
82
+ | 0.0804 | 0.4039 | 1600 | 0.0538 | 0.6112 |
83
+ | 0.083 | 0.4166 | 1650 | 0.0579 | 0.6048 |
84
+ | 0.0701 | 0.4292 | 1700 | 0.0674 | 0.6045 |
85
+ | 0.0721 | 0.4418 | 1750 | 0.0491 | 0.5979 |
86
+ | 0.0765 | 0.4544 | 1800 | 0.0439 | nan |
87
+ | 0.0692 | 0.4671 | 1850 | 0.0468 | 0.6058 |
88
+ | 0.0761 | 0.4797 | 1900 | 0.0574 | 0.6125 |
89
+ | 0.0757 | 0.4923 | 1950 | 0.0569 | 0.6126 |
90
+ | 0.0654 | 0.5049 | 2000 | 0.0549 | 0.6095 |
91
+ | 0.0706 | 0.5175 | 2050 | 0.0423 | 0.6042 |
92
+ | 0.0647 | 0.5302 | 2100 | 0.0463 | 0.6056 |
93
+ | 0.0626 | 0.5428 | 2150 | 0.0478 | 0.6048 |
94
 
95
 
96
  ### Framework versions
p_object.json CHANGED
The diff for this file is too large to render. See raw diff
 
prediction_reference.json CHANGED
The diff for this file is too large to render. See raw diff