Hugging Face's logo

CynthiaCR
/
emotions_classifier

Image Classification
Transformers
TensorFlow
vit
generated_from_keras_callback
Model card Files
xet
 Community
1
CynthiaCR commited on
Commit
6794f2e
·
1 Parent(s): 1e86f57

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. config.json +1 -1
  3. tf_model.h5 +2 -2
README.md CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 1.4518
18
- - Validation Loss: 1.8093
19
- - Train Accuracy: 0.2062
20
  - Epoch: 19
21
 
22
  ## Model description
@@ -43,31 +43,31 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
- | 2.1237 | 2.0984 | 0.1125 | 0 |
47
- | 2.0901 | 2.0798 | 0.1125 | 1 |
48
- | 2.0462 | 1.9204 | 0.2687 | 2 |
49
- | 1.9321 | 2.0251 | 0.2875 | 3 |
50
- | 1.8507 | 1.7461 | 0.225 | 4 |
51
- | 1.8616 | 1.8823 | 0.2687 | 5 |
52
- | 1.8506 | 1.7999 | 0.2812 | 6 |
53
- | 1.6719 | 1.6320 | 0.2875 | 7 |
54
- | 1.7967 | 1.6512 | 0.2812 | 8 |
55
- | 1.6516 | 1.7399 | 0.2313 | 9 |
56
- | 1.6067 | 1.7215 | 0.275 | 10 |
57
- | 1.6551 | 1.5827 | 0.3438 | 11 |
58
- | 1.5167 | 1.5616 | 0.3312 | 12 |
59
- | 1.4866 | 1.5315 | 0.3563 | 13 |
60
- | 1.4716 | 1.5366 | 0.3312 | 14 |
61
- | 1.4446 | 2.0898 | 0.2875 | 15 |
62
- | 1.5621 | 1.5107 | 0.325 | 16 |
63
- | 1.4635 | 1.5549 | 0.3125 | 17 |
64
- | 1.4736 | 1.6316 | 0.325 | 18 |
65
- | 1.4518 | 1.8093 | 0.2062 | 19 |
66
 
67
 
68
  ### Framework versions
69
 
70
- - Transformers 4.29.1
71
  - TensorFlow 2.12.0
72
  - Datasets 2.12.0
73
  - Tokenizers 0.13.3
 
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.0778
18
+ - Validation Loss: 2.0976
19
+ - Train Accuracy: 0.1062
20
  - Epoch: 19
21
 
22
  ## Model description
 
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 2.0842 | 2.0801 | 0.1625 | 0 |
47
+ | 2.0806 | 2.0828 | 0.1 | 1 |
48
+ | 2.0807 | 2.0852 | 0.1 | 2 |
49
+ | 2.0813 | 2.0829 | 0.1562 | 3 |
50
+ | 2.0793 | 2.0806 | 0.1 | 4 |
51
+ | 2.0921 | 2.1075 | 0.1 | 5 |
52
+ | 2.0990 | 2.0887 | 0.1437 | 6 |
53
+ | 2.0939 | 2.0843 | 0.1437 | 7 |
54
+ | 2.0864 | 2.0863 | 0.125 | 8 |
55
+ | 2.0846 | 2.0791 | 0.1313 | 9 |
56
+ | 2.0827 | 2.0852 | 0.1 | 10 |
57
+ | 2.0823 | 2.0857 | 0.1 | 11 |
58
+ | 2.0813 | 2.0846 | 0.1062 | 12 |
59
+ | 2.0808 | 2.0841 | 0.1187 | 13 |
60
+ | 2.0813 | 2.0851 | 0.1187 | 14 |
61
+ | 2.0822 | 2.0833 | 0.1 | 15 |
62
+ | 2.0804 | 2.0838 | 0.1 | 16 |
63
+ | 2.0799 | 2.0834 | 0.1 | 17 |
64
+ | 2.0786 | 2.0837 | 0.1 | 18 |
65
+ | 2.0778 | 2.0976 | 0.1062 | 19 |
66
 
67
 
68
  ### Framework versions
69
 
70
+ - Transformers 4.29.2
71
  - TensorFlow 2.12.0
72
  - Datasets 2.12.0
73
  - Tokenizers 0.13.3
config.json CHANGED
@@ -38,5 +38,5 @@
38
  "num_hidden_layers": 12,
39
  "patch_size": 16,
40
  "qkv_bias": true,
41
- "transformers_version": "4.29.1"
42
  }
 
38
  "num_hidden_layers": 12,
39
  "patch_size": 16,
40
  "qkv_bias": true,
41
+ "transformers_version": "4.29.2"
42
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cff8ba6d2ed641cfbd6978114623b1881f11a37d560005a009a2bf2ec1ba8fce
3
- size 343504568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0dc3c3056729a46a1d81de423e25170fa1350d6262b0d1bf3de76b17d38548c
3
+ size 343488184