Hugging Face's logo

khaingsmon
/
test-hasy-6

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
khaingsmon commited on
Commit
90d6800
•
1 Parent(s): 249d16e

Model save

Browse files
Files changed (3) hide show
  1. README.md +56 -9
  2. model.safetensors +1 -1
  3. runs/Mar12_19-07-22_30303fe9e772/events.out.tfevents.1710270445.30303fe9e772.1893.8 +2 -2
README.md CHANGED
@@ -2,7 +2,6 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
- - image-classification
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
@@ -16,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # test-hasy-6
18
 
19
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the HASY dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.8365
22
- - Accuracy: 0.4969
23
 
24
  ## Model description
25
 
@@ -44,15 +43,63 @@ The following hyperparameters were used during training:
44
  - seed: 1787
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 2
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 3.5095 | 1.0 | 541 | 2.9905 | 0.4636 |
55
- | 2.8453 | 2.0 | 1082 | 2.8365 | 0.4969 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
15
 
16
  # test-hasy-6
17
 
18
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6566
21
+ - Accuracy: 0.7942
22
 
23
  ## Model description
24
 
 
43
  - seed: 1787
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 3.0857 | 1.0 | 541 | 2.4484 | 0.5572 |
54
+ | 2.3006 | 2.0 | 1082 | 2.1588 | 0.5904 |
55
+ | 2.4406 | 3.0 | 1623 | 1.8879 | 0.6445 |
56
+ | 2.342 | 4.0 | 2164 | 1.7122 | 0.6674 |
57
+ | 2.1852 | 5.0 | 2705 | 1.5467 | 0.6923 |
58
+ | 1.9535 | 6.0 | 3246 | 1.4113 | 0.7048 |
59
+ | 1.9061 | 7.0 | 3787 | 1.3136 | 0.6881 |
60
+ | 1.5934 | 8.0 | 4328 | 1.2059 | 0.7089 |
61
+ | 1.8755 | 9.0 | 4869 | 1.1638 | 0.7173 |
62
+ | 1.6319 | 10.0 | 5410 | 1.1024 | 0.7235 |
63
+ | 1.5899 | 11.0 | 5951 | 1.0375 | 0.7339 |
64
+ | 1.6427 | 12.0 | 6492 | 0.9656 | 0.7526 |
65
+ | 1.8022 | 13.0 | 7033 | 0.9760 | 0.7422 |
66
+ | 1.7161 | 14.0 | 7574 | 0.8952 | 0.7609 |
67
+ | 1.2123 | 15.0 | 8115 | 0.8750 | 0.7692 |
68
+ | 1.5721 | 16.0 | 8656 | 0.8586 | 0.7755 |
69
+ | 1.7482 | 17.0 | 9197 | 0.8279 | 0.7755 |
70
+ | 1.5992 | 18.0 | 9738 | 0.8321 | 0.7547 |
71
+ | 1.8179 | 19.0 | 10279 | 0.7898 | 0.7817 |
72
+ | 1.2744 | 20.0 | 10820 | 0.7984 | 0.7672 |
73
+ | 1.2221 | 21.0 | 11361 | 0.7757 | 0.7734 |
74
+ | 1.4893 | 22.0 | 11902 | 0.7512 | 0.7817 |
75
+ | 1.5184 | 23.0 | 12443 | 0.7512 | 0.7817 |
76
+ | 1.6562 | 24.0 | 12984 | 0.7514 | 0.7796 |
77
+ | 1.4148 | 25.0 | 13525 | 0.7241 | 0.7817 |
78
+ | 1.2765 | 26.0 | 14066 | 0.6907 | 0.8046 |
79
+ | 1.3378 | 27.0 | 14607 | 0.7132 | 0.7900 |
80
+ | 1.5446 | 28.0 | 15148 | 0.6973 | 0.7963 |
81
+ | 1.1969 | 29.0 | 15689 | 0.7010 | 0.7921 |
82
+ | 1.3721 | 30.0 | 16230 | 0.6928 | 0.8004 |
83
+ | 1.4051 | 31.0 | 16771 | 0.6976 | 0.7921 |
84
+ | 1.1004 | 32.0 | 17312 | 0.6785 | 0.8004 |
85
+ | 1.2668 | 33.0 | 17853 | 0.6883 | 0.7817 |
86
+ | 1.0728 | 34.0 | 18394 | 0.6924 | 0.7859 |
87
+ | 1.1856 | 35.0 | 18935 | 0.6840 | 0.7921 |
88
+ | 1.2387 | 36.0 | 19476 | 0.6739 | 0.8025 |
89
+ | 1.5242 | 37.0 | 20017 | 0.6554 | 0.7963 |
90
+ | 1.351 | 38.0 | 20558 | 0.6736 | 0.7942 |
91
+ | 1.2441 | 39.0 | 21099 | 0.6659 | 0.8046 |
92
+ | 1.2113 | 40.0 | 21640 | 0.6709 | 0.7983 |
93
+ | 1.1608 | 41.0 | 22181 | 0.6630 | 0.7983 |
94
+ | 1.266 | 42.0 | 22722 | 0.6693 | 0.8004 |
95
+ | 0.9426 | 43.0 | 23263 | 0.6639 | 0.8046 |
96
+ | 1.0066 | 44.0 | 23804 | 0.6636 | 0.8025 |
97
+ | 1.0856 | 45.0 | 24345 | 0.6530 | 0.8004 |
98
+ | 1.0128 | 46.0 | 24886 | 0.6506 | 0.8025 |
99
+ | 1.0369 | 47.0 | 25427 | 0.6617 | 0.8025 |
100
+ | 1.1458 | 48.0 | 25968 | 0.6546 | 0.8004 |
101
+ | 1.0696 | 49.0 | 26509 | 0.6597 | 0.7942 |
102
+ | 1.2227 | 50.0 | 27050 | 0.6566 | 0.7942 |
103
 
104
 
105
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21c61c711feb804af8c12117fec2d8cde8862507a09d7e3355484644173d3ad4
3
  size 343599256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc74f24641091ed0f0b5ddecb909fcfb16ed06b0535f8f41167312615b27bab
3
  size 343599256
runs/Mar12_19-07-22_30303fe9e772/events.out.tfevents.1710270445.30303fe9e772.1893.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dc6283afdfb693389a39884c31d36a45ca2b0835cd0d7970b3ae352df6c087e
3
- size 599947
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a3d6788e3636b63a9dc632346c6bd9ae771a853b613865693b8dec6f2d8e7e
3
+ size 600307