Hugging Face's logo

YufeiWeng
/
donut-base-beans

Image Classification
Transformers
Safetensors
beit
vision
Generated from Trainer
Model card Files Community
YufeiWeng commited on
Commit
8b2c166
·
verified ·
1 Parent(s): de97e4e

Model save

Browse files
Files changed (2) hide show
  1. README.md +18 -66
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,8 +1,6 @@
1
  ---
2
  base_model: microsoft/dit-base-finetuned-rvlcdip
3
  tags:
4
- - image-classification
5
- - vision
6
  - generated_from_trainer
7
  metrics:
8
  - f1
@@ -18,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  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.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0404
22
- - F1: 0.6134
23
 
24
  ## Model description
25
 
@@ -38,73 +36,27 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 3e-05
42
- - train_batch_size: 64
43
- - eval_batch_size: 64
44
  - seed: 1337
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
- - lr_scheduler_type: linear
47
- - training_steps: 10000
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | F1 | Validation Loss |
52
- |:-------------:|:------:|:----:|:------:|:---------------:|
53
- | 0.1165 | 0.0126 | 50 | 0.4177 | 0.0642 |
54
- | 0.0942 | 0.0252 | 100 | 0.4772 | 0.0485 |
55
- | 0.1076 | 0.0379 | 150 | 0.4643 | 0.0584 |
56
- | 0.1103 | 0.0505 | 200 | nan | 0.0446 |
57
- | 0.0873 | 0.0631 | 250 | 0.5313 | 0.0518 |
58
- | 0.1053 | 0.0757 | 300 | 0.5329 | 0.0736 |
59
- | 0.0797 | 0.0884 | 350 | 0.5326 | 0.0726 |
60
- | 0.0857 | 0.1010 | 400 | 0.5498 | 0.0693 |
61
- | 0.0885 | 0.1136 | 450 | nan | 0.0917 |
62
- | 0.102 | 0.1262 | 500 | 0.5649 | 0.0580 |
63
- | 0.0716 | 0.1389 | 550 | 0.5381 | 0.0797 |
64
- | 0.0854 | 0.1515 | 600 | 0.5718 | 0.0744 |
65
- | 0.089 | 0.1641 | 650 | 0.5790 | 0.0504 |
66
- | 0.0721 | 0.1767 | 700 | 0.5727 | 0.0618 |
67
- | 0.0721 | 0.1893 | 750 | 0.5904 | 0.0703 |
68
- | 0.0865 | 0.2020 | 800 | 0.5953 | 0.0588 |
69
- | 0.0767 | 0.2146 | 850 | 0.5918 | 0.0437 |
70
- | 0.0773 | 0.2272 | 900 | 0.5957 | 0.0568 |
71
- | 0.0748 | 0.2398 | 950 | 0.5942 | 0.0465 |
72
- | 0.0761 | 0.2525 | 1000 | nan | 0.0660 |
73
- | 0.0855 | 0.2651 | 1050 | 0.5964 | 0.0491 |
74
- | 0.0832 | 0.2777 | 1100 | 0.6048 | 0.0498 |
75
- | 0.0821 | 0.2903 | 1150 | 0.6032 | 0.0597 |
76
- | 0.0715 | 0.3030 | 1200 | nan | 0.0643 |
77
- | 0.085 | 0.3156 | 1250 | 0.6054 | 0.0659 |
78
- | 0.0826 | 0.3282 | 1300 | 0.6012 | 0.0556 |
79
- | 0.064 | 0.3408 | 1350 | nan | 0.0564 |
80
- | 0.0854 | 0.3534 | 1400 | nan | 0.0552 |
81
- | 0.0702 | 0.3661 | 1450 | 0.6061 | 0.0675 |
82
- | 0.0771 | 0.3787 | 1500 | nan | 0.0578 |
83
- | 0.08 | 0.3913 | 1550 | nan | 0.0492 |
84
- | 0.0804 | 0.4039 | 1600 | 0.6112 | 0.0538 |
85
- | 0.083 | 0.4166 | 1650 | 0.6048 | 0.0579 |
86
- | 0.0701 | 0.4292 | 1700 | 0.6045 | 0.0674 |
87
- | 0.0721 | 0.4418 | 1750 | 0.5979 | 0.0491 |
88
- | 0.0765 | 0.4544 | 1800 | nan | 0.0439 |
89
- | 0.0692 | 0.4671 | 1850 | 0.6058 | 0.0468 |
90
- | 0.0761 | 0.4797 | 1900 | 0.6125 | 0.0574 |
91
- | 0.0757 | 0.4923 | 1950 | 0.6126 | 0.0569 |
92
- | 0.0654 | 0.5049 | 2000 | 0.6095 | 0.0549 |
93
- | 0.0736 | 0.5175 | 2050 | 0.0538 | 0.6122 |
94
- | 0.0685 | 0.5302 | 2100 | 0.0485 | 0.6104 |
95
- | 0.0726 | 0.5428 | 2150 | 0.0566 | 0.6120 |
96
- | 0.0731 | 0.5554 | 2200 | 0.0585 | 0.6112 |
97
- | 0.0722 | 0.5680 | 2250 | 0.0589 | 0.6140 |
98
- | 0.0819 | 0.5807 | 2300 | 0.0505 | 0.6122 |
99
- | 0.0694 | 0.5933 | 2350 | 0.0537 | 0.6101 |
100
- | 0.0705 | 0.6059 | 2400 | 0.0646 | 0.6130 |
101
- | 0.0702 | 0.6185 | 2450 | 0.0462 | 0.6124 |
102
- | 0.0709 | 0.6312 | 2500 | 0.0404 | 0.6134 |
103
- | 0.0804 | 0.6438 | 2550 | 0.0478 | 0.6123 |
104
- | 0.0666 | 0.6564 | 2600 | 0.0455 | 0.6104 |
105
- | 0.0749 | 0.6690 | 2650 | 0.0479 | 0.6132 |
106
- | 0.067 | 0.6816 | 2700 | 0.0558 | 0.6132 |
107
- | 0.068 | 0.6943 | 2750 | 0.0539 | 0.6108 |
108
 
109
 
110
  ### Framework versions
 
1
  ---
2
  base_model: microsoft/dit-base-finetuned-rvlcdip
3
  tags:
 
 
4
  - generated_from_trainer
5
  metrics:
6
  - f1
 
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: 0.2283
20
+ - F1: 0.2395
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0005
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: cosine
45
+ - training_steps: 30000
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
50
+ |:-------------:|:------:|:----:|:---------------:|:------:|
51
+ | No log | 0.2524 | 500 | 0.1623 | 0.3040 |
52
+ | 0.1656 | 0.5048 | 1000 | 0.4307 | nan |
53
+ | 0.1656 | 0.7572 | 1500 | 0.1493 | nan |
54
+ | 0.14 | 1.0096 | 2000 | 0.1870 | 0.3826 |
55
+ | 0.14 | 1.2620 | 2500 | 0.1076 | nan |
56
+ | 0.1285 | 1.5144 | 3000 | 0.0896 | 0.3812 |
57
+ | 0.1285 | 1.7668 | 3500 | 0.1405 | nan |
58
+ | 0.123 | 2.0192 | 4000 | 0.2061 | nan |
59
+ | 0.123 | 2.2716 | 4500 | 0.2283 | 0.2395 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebd66e9c6ab4a89ecbfa52c398511b83e56b57c4771e7be249ebf1f269583f5b
3
  size 343258940
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e10221269d5b6d8c69825ac3399722b824a8769e7a9c1027a71b67cf1d27c6ba
3
  size 343258940