Hugging Face's logo

Hemg
/
sign-language-classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
 Metrics Community
Hemg commited on
Commit
560e5ef
·
verified ·
1 Parent(s): c2c6b09

Model save

Browse files
Files changed (3) hide show
  1. README.md +35 -19
  2. model.safetensors +1 -1
  3. runs/Mar15_10-52-25_b37b964875e5/events.out.tfevents.1710499946.b37b964875e5.34.2 +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
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 an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2240
21
- - Accuracy: 0.935
22
 
23
  ## Model description
24
 
@@ -46,28 +46,44 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.01
49
- - num_epochs: 16
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 2.5191 | 1.0 | 100 | 1.5326 | 0.8025 |
56
- | 1.0907 | 2.0 | 200 | 0.7187 | 0.8675 |
57
- | 0.6314 | 3.0 | 300 | 0.5403 | 0.8525 |
58
- | 0.549 | 4.0 | 400 | 0.4672 | 0.89 |
59
- | 0.3687 | 5.0 | 500 | 0.3414 | 0.8925 |
60
- | 0.354 | 6.0 | 600 | 0.3278 | 0.895 |
61
- | 0.316 | 7.0 | 700 | 0.2925 | 0.9175 |
62
- | 0.2885 | 8.0 | 800 | 0.2866 | 0.915 |
63
- | 0.2644 | 9.0 | 900 | 0.1893 | 0.9475 |
64
- | 0.2222 | 10.0 | 1000 | 0.1593 | 0.9575 |
65
- | 0.223 | 11.0 | 1100 | 0.2601 | 0.9075 |
66
- | 0.1745 | 12.0 | 1200 | 0.2564 | 0.925 |
67
- | 0.1751 | 13.0 | 1300 | 0.1896 | 0.945 |
68
- | 0.1589 | 14.0 | 1400 | 0.1918 | 0.95 |
69
- | 0.172 | 15.0 | 1500 | 0.1579 | 0.9575 |
70
- | 0.1304 | 16.0 | 1600 | 0.2240 | 0.935 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
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 an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1351
21
+ - Accuracy: 0.96
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.01
49
+ - num_epochs: 32
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 2.6016 | 1.0 | 100 | 1.5038 | 0.8 |
56
+ | 1.1072 | 2.0 | 200 | 0.6959 | 0.8675 |
57
+ | 0.6195 | 3.0 | 300 | 0.5236 | 0.87 |
58
+ | 0.5559 | 4.0 | 400 | 0.4819 | 0.87 |
59
+ | 0.389 | 5.0 | 500 | 0.3392 | 0.9 |
60
+ | 0.3878 | 6.0 | 600 | 0.3600 | 0.9025 |
61
+ | 0.3309 | 7.0 | 700 | 0.3312 | 0.9075 |
62
+ | 0.3397 | 8.0 | 800 | 0.2596 | 0.9225 |
63
+ | 0.3033 | 9.0 | 900 | 0.2056 | 0.935 |
64
+ | 0.2765 | 10.0 | 1000 | 0.2802 | 0.9175 |
65
+ | 0.2846 | 11.0 | 1100 | 0.3276 | 0.9025 |
66
+ | 0.2443 | 12.0 | 1200 | 0.3689 | 0.8975 |
67
+ | 0.2682 | 13.0 | 1300 | 0.2805 | 0.915 |
68
+ | 0.2053 | 14.0 | 1400 | 0.2437 | 0.9225 |
69
+ | 0.2453 | 15.0 | 1500 | 0.2646 | 0.92 |
70
+ | 0.1896 | 16.0 | 1600 | 0.2489 | 0.925 |
71
+ | 0.1841 | 17.0 | 1700 | 0.2393 | 0.9275 |
72
+ | 0.1406 | 18.0 | 1800 | 0.1935 | 0.945 |
73
+ | 0.1573 | 19.0 | 1900 | 0.2544 | 0.92 |
74
+ | 0.155 | 20.0 | 2000 | 0.1940 | 0.9475 |
75
+ | 0.1563 | 21.0 | 2100 | 0.2021 | 0.9325 |
76
+ | 0.133 | 22.0 | 2200 | 0.2413 | 0.9325 |
77
+ | 0.117 | 23.0 | 2300 | 0.1939 | 0.9375 |
78
+ | 0.1455 | 24.0 | 2400 | 0.1685 | 0.9575 |
79
+ | 0.144 | 25.0 | 2500 | 0.1787 | 0.9475 |
80
+ | 0.1119 | 26.0 | 2600 | 0.1511 | 0.96 |
81
+ | 0.1053 | 27.0 | 2700 | 0.1308 | 0.965 |
82
+ | 0.0964 | 28.0 | 2800 | 0.1042 | 0.9725 |
83
+ | 0.0938 | 29.0 | 2900 | 0.1751 | 0.9425 |
84
+ | 0.0881 | 30.0 | 3000 | 0.1066 | 0.965 |
85
+ | 0.0854 | 31.0 | 3100 | 0.1116 | 0.97 |
86
+ | 0.1002 | 32.0 | 3200 | 0.1351 | 0.96 |
87
 
88
 
89
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efb9262b2bd580567c0d102142e34aca1862c86aad8fac73426c3ff5e4d4f1a9
3
  size 343328568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f537f4a782e5413db77772dcd7d71503ba856c0309049849bf39fa317db51ba
3
  size 343328568
runs/Mar15_10-52-25_b37b964875e5/events.out.tfevents.1710499946.b37b964875e5.34.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb45e8d1b87ff63860d1a6b2471cc61d23adef11649e19e47acce16e6f90fcc
3
- size 22122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540c0bb27965f500e228c494e2bd8e03c1b8483f84a1d24240846fb9cda9e332
3
+ size 23010