Hugging Face's logo

mhdiqbalpradipta
/
emotion_classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
mhdiqbalpradipta commited on
Commit
d051010
·
verified ·
1 Parent(s): 663c1a1

End of training

Browse files
Files changed (1) hide show
  1. README.md +8 -65
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.625
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [dennisjooo/emotion_classification](https://huggingface.co/dennisjooo/emotion_classification) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.1505
36
- - Accuracy: 0.625
37
 
38
  ## Model description
39
 
@@ -58,78 +58,21 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: cosine_with_restarts
61
- - num_epochs: 60
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.6887 | 1.0 | 40 | 1.2010 | 0.55 |
69
- | 0.6532 | 2.0 | 80 | 1.1886 | 0.5875 |
70
- | 0.6007 | 3.0 | 120 | 1.0654 | 0.6562 |
71
- | 0.5773 | 4.0 | 160 | 1.1253 | 0.5938 |
72
- | 0.5632 | 5.0 | 200 | 1.1287 | 0.5687 |
73
- | 0.5642 | 6.0 | 240 | 1.1198 | 0.5938 |
74
- | 0.5136 | 7.0 | 280 | 1.2047 | 0.5625 |
75
- | 0.4931 | 8.0 | 320 | 1.1474 | 0.6 |
76
- | 0.4867 | 9.0 | 360 | 1.1146 | 0.6188 |
77
- | 0.4428 | 10.0 | 400 | 1.1561 | 0.6188 |
78
- | 0.4345 | 11.0 | 440 | 1.0993 | 0.6188 |
79
- | 0.4006 | 12.0 | 480 | 1.1786 | 0.5813 |
80
- | 0.4052 | 13.0 | 520 | 1.0929 | 0.6438 |
81
- | 0.4215 | 14.0 | 560 | 1.1574 | 0.6 |
82
- | 0.3702 | 15.0 | 600 | 1.2048 | 0.5625 |
83
- | 0.3692 | 16.0 | 640 | 1.2477 | 0.6 |
84
- | 0.3475 | 17.0 | 680 | 1.1999 | 0.5687 |
85
- | 0.3374 | 18.0 | 720 | 1.1560 | 0.6125 |
86
- | 0.3141 | 19.0 | 760 | 1.1571 | 0.5813 |
87
- | 0.2949 | 20.0 | 800 | 1.1420 | 0.6 |
88
- | 0.2972 | 21.0 | 840 | 1.2070 | 0.6 |
89
- | 0.317 | 22.0 | 880 | 1.2712 | 0.55 |
90
- | 0.2805 | 23.0 | 920 | 1.2785 | 0.5375 |
91
- | 0.2521 | 24.0 | 960 | 1.2000 | 0.575 |
92
- | 0.2951 | 25.0 | 1000 | 1.2287 | 0.5875 |
93
- | 0.2878 | 26.0 | 1040 | 1.3343 | 0.5625 |
94
- | 0.2564 | 27.0 | 1080 | 1.1686 | 0.5813 |
95
- | 0.2755 | 28.0 | 1120 | 1.3571 | 0.575 |
96
- | 0.3148 | 29.0 | 1160 | 1.3059 | 0.5563 |
97
- | 0.2942 | 30.0 | 1200 | 1.2678 | 0.5875 |
98
- | 0.2867 | 31.0 | 1240 | 1.2240 | 0.6062 |
99
- | 0.2489 | 32.0 | 1280 | 1.2434 | 0.5625 |
100
- | 0.2747 | 33.0 | 1320 | 1.1920 | 0.6312 |
101
- | 0.2279 | 34.0 | 1360 | 1.3587 | 0.5563 |
102
- | 0.2446 | 35.0 | 1400 | 1.2098 | 0.625 |
103
- | 0.1897 | 36.0 | 1440 | 1.1853 | 0.6375 |
104
- | 0.2076 | 37.0 | 1480 | 1.3183 | 0.6125 |
105
- | 0.2174 | 38.0 | 1520 | 1.2557 | 0.6312 |
106
- | 0.2297 | 39.0 | 1560 | 1.2031 | 0.6125 |
107
- | 0.2082 | 40.0 | 1600 | 1.2217 | 0.6188 |
108
- | 0.2457 | 41.0 | 1640 | 1.2759 | 0.6312 |
109
- | 0.2003 | 42.0 | 1680 | 1.2721 | 0.6188 |
110
- | 0.2394 | 43.0 | 1720 | 1.3591 | 0.5875 |
111
- | 0.2233 | 44.0 | 1760 | 1.2542 | 0.6375 |
112
- | 0.2181 | 45.0 | 1800 | 1.2548 | 0.6 |
113
- | 0.19 | 46.0 | 1840 | 1.1620 | 0.6188 |
114
- | 0.2213 | 47.0 | 1880 | 1.1367 | 0.6562 |
115
- | 0.211 | 48.0 | 1920 | 1.1482 | 0.6625 |
116
- | 0.2209 | 49.0 | 1960 | 1.2520 | 0.6188 |
117
- | 0.236 | 50.0 | 2000 | 1.3048 | 0.5813 |
118
- | 0.1973 | 51.0 | 2040 | 1.1874 | 0.6062 |
119
- | 0.2207 | 52.0 | 2080 | 1.2998 | 0.6125 |
120
- | 0.196 | 53.0 | 2120 | 1.2363 | 0.6188 |
121
- | 0.1915 | 54.0 | 2160 | 1.2635 | 0.625 |
122
- | 0.2543 | 55.0 | 2200 | 1.2311 | 0.6312 |
123
- | 0.2088 | 56.0 | 2240 | 1.2187 | 0.5875 |
124
- | 0.2018 | 57.0 | 2280 | 1.2326 | 0.5813 |
125
- | 0.1957 | 58.0 | 2320 | 1.3425 | 0.5875 |
126
- | 0.2228 | 59.0 | 2360 | 1.2038 | 0.6188 |
127
- | 0.1957 | 60.0 | 2400 | 1.1505 | 0.625 |
128
 
129
 
130
  ### Framework versions
131
 
132
  - Transformers 4.35.2
133
  - Pytorch 2.1.0+cu121
134
- - Datasets 2.16.1
135
  - Tokenizers 0.15.1
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.64375
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [dennisjooo/emotion_classification](https://huggingface.co/dennisjooo/emotion_classification) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.1270
36
+ - Accuracy: 0.6438
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: cosine_with_restarts
61
+ - num_epochs: 3
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.2012 | 1.0 | 40 | 1.4178 | 0.5062 |
69
+ | 0.2339 | 2.0 | 80 | 1.2855 | 0.5875 |
70
+ | 0.2162 | 3.0 | 120 | 1.1270 | 0.6438 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
74
 
75
  - Transformers 4.35.2
76
  - Pytorch 2.1.0+cu121
77
+ - Datasets 2.17.0
78
  - Tokenizers 0.15.1