Hugging Face's logo

krismp
/
emotion_recognition

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
3
krismp commited on
Commit
c5b1785
•
1 Parent(s): 1093dc6

End of training

Browse files
Files changed (4) hide show
  1. README.md +59 -56
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.125
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.0993
36
- - Accuracy: 0.125
37
 
38
  ## Model description
39
 
@@ -52,73 +52,76 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.0005
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
 
61
  - num_epochs: 50
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 2.0986 | 0.125 |
68
- | No log | 2.0 | 80 | 2.0816 | 0.125 |
69
- | No log | 3.0 | 120 | 2.0798 | 0.125 |
70
- | No log | 4.0 | 160 | 2.0765 | 0.125 |
71
- | No log | 5.0 | 200 | 2.0765 | 0.125 |
72
- | No log | 6.0 | 240 | 2.0820 | 0.125 |
73
- | No log | 7.0 | 280 | 2.0796 | 0.125 |
74
- | No log | 8.0 | 320 | 2.0826 | 0.125 |
75
- | No log | 9.0 | 360 | 2.0759 | 0.125 |
76
- | No log | 10.0 | 400 | 2.0799 | 0.125 |
77
- | No log | 11.0 | 440 | 2.0593 | 0.125 |
78
- | No log | 12.0 | 480 | 2.0813 | 0.125 |
79
- | 2.0843 | 13.0 | 520 | 2.0817 | 0.125 |
80
- | 2.0843 | 14.0 | 560 | 2.1626 | 0.125 |
81
- | 2.0843 | 15.0 | 600 | 2.1105 | 0.125 |
82
- | 2.0843 | 16.0 | 640 | 2.0921 | 0.125 |
83
- | 2.0843 | 17.0 | 680 | 2.0878 | 0.125 |
84
- | 2.0843 | 18.0 | 720 | 2.0877 | 0.125 |
85
- | 2.0843 | 19.0 | 760 | 2.0815 | 0.125 |
86
- | 2.0843 | 20.0 | 800 | 2.0812 | 0.125 |
87
- | 2.0843 | 21.0 | 840 | 2.0810 | 0.125 |
88
- | 2.0843 | 22.0 | 880 | 2.0796 | 0.125 |
89
- | 2.0843 | 23.0 | 920 | 2.0798 | 0.125 |
90
- | 2.0843 | 24.0 | 960 | 2.0808 | 0.125 |
91
- | 2.0948 | 25.0 | 1000 | 2.0812 | 0.125 |
92
- | 2.0948 | 26.0 | 1040 | 2.0806 | 0.125 |
93
- | 2.0948 | 27.0 | 1080 | 2.0797 | 0.125 |
94
- | 2.0948 | 28.0 | 1120 | 2.0795 | 0.125 |
95
- | 2.0948 | 29.0 | 1160 | 2.0801 | 0.125 |
96
- | 2.0948 | 30.0 | 1200 | 2.0792 | 0.125 |
97
- | 2.0948 | 31.0 | 1240 | 2.0783 | 0.125 |
98
- | 2.0948 | 32.0 | 1280 | 2.0792 | 0.125 |
99
- | 2.0948 | 33.0 | 1320 | 2.0786 | 0.125 |
100
- | 2.0948 | 34.0 | 1360 | 2.0769 | 0.125 |
101
- | 2.0948 | 35.0 | 1400 | 2.0686 | 0.125 |
102
- | 2.0948 | 36.0 | 1440 | 2.0616 | 0.125 |
103
- | 2.0948 | 37.0 | 1480 | 2.0653 | 0.125 |
104
- | 2.0804 | 38.0 | 1520 | 2.0970 | 0.125 |
105
- | 2.0804 | 39.0 | 1560 | 2.0815 | 0.125 |
106
- | 2.0804 | 40.0 | 1600 | 2.0743 | 0.125 |
107
- | 2.0804 | 41.0 | 1640 | 2.0802 | 0.125 |
108
- | 2.0804 | 42.0 | 1680 | 2.0655 | 0.125 |
109
- | 2.0804 | 43.0 | 1720 | 2.0768 | 0.125 |
110
- | 2.0804 | 44.0 | 1760 | 2.0642 | 0.125 |
111
- | 2.0804 | 45.0 | 1800 | 2.0637 | 0.125 |
112
- | 2.0804 | 46.0 | 1840 | 2.0687 | 0.125 |
113
- | 2.0804 | 47.0 | 1880 | 2.0603 | 0.125 |
114
- | 2.0804 | 48.0 | 1920 | 2.0507 | 0.125 |
115
- | 2.0804 | 49.0 | 1960 | 2.0395 | 0.125 |
116
- | 2.0589 | 50.0 | 2000 | 2.0600 | 0.125 |
117
 
118
 
119
  ### Framework versions
120
 
121
- - Transformers 4.33.2
122
- - Pytorch 2.0.1+cu118
123
  - Datasets 2.14.5
124
  - Tokenizers 0.13.3
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.175
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.3469
36
+ - Accuracy: 0.175
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 50
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 10 | 2.0721 | 0.125 |
71
+ | No log | 2.0 | 20 | 2.0633 | 0.125 |
72
+ | No log | 3.0 | 30 | 2.0038 | 0.125 |
73
+ | No log | 4.0 | 40 | 1.9097 | 0.125 |
74
+ | No log | 5.0 | 50 | 1.7412 | 0.125 |
75
+ | No log | 6.0 | 60 | 1.6189 | 0.05 |
76
+ | No log | 7.0 | 70 | 1.5343 | 0.0375 |
77
+ | No log | 8.0 | 80 | 1.4746 | 0.0688 |
78
+ | No log | 9.0 | 90 | 1.4330 | 0.0938 |
79
+ | No log | 10.0 | 100 | 1.4130 | 0.15 |
80
+ | No log | 11.0 | 110 | 1.3735 | 0.1062 |
81
+ | No log | 12.0 | 120 | 1.3516 | 0.1062 |
82
+ | No log | 13.0 | 130 | 1.2838 | 0.1375 |
83
+ | No log | 14.0 | 140 | 1.3058 | 0.1187 |
84
+ | No log | 15.0 | 150 | 1.3116 | 0.1 |
85
+ | No log | 16.0 | 160 | 1.3269 | 0.1313 |
86
+ | No log | 17.0 | 170 | 1.2624 | 0.1062 |
87
+ | No log | 18.0 | 180 | 1.3285 | 0.1187 |
88
+ | No log | 19.0 | 190 | 1.3490 | 0.1437 |
89
+ | No log | 20.0 | 200 | 1.2592 | 0.1375 |
90
+ | No log | 21.0 | 210 | 1.3600 | 0.0938 |
91
+ | No log | 22.0 | 220 | 1.2835 | 0.1313 |
92
+ | No log | 23.0 | 230 | 1.2842 | 0.1375 |
93
+ | No log | 24.0 | 240 | 1.2840 | 0.1 |
94
+ | No log | 25.0 | 250 | 1.2456 | 0.1313 |
95
+ | No log | 26.0 | 260 | 1.2960 | 0.1562 |
96
+ | No log | 27.0 | 270 | 1.3208 | 0.1375 |
97
+ | No log | 28.0 | 280 | 1.3207 | 0.1375 |
98
+ | No log | 29.0 | 290 | 1.2892 | 0.175 |
99
+ | No log | 30.0 | 300 | 1.2837 | 0.1812 |
100
+ | No log | 31.0 | 310 | 1.3548 | 0.1562 |
101
+ | No log | 32.0 | 320 | 1.4371 | 0.1437 |
102
+ | No log | 33.0 | 330 | 1.4219 | 0.1562 |
103
+ | No log | 34.0 | 340 | 1.4033 | 0.1875 |
104
+ | No log | 35.0 | 350 | 1.4505 | 0.1437 |
105
+ | No log | 36.0 | 360 | 1.2975 | 0.1562 |
106
+ | No log | 37.0 | 370 | 1.3906 | 0.1562 |
107
+ | No log | 38.0 | 380 | 1.3547 | 0.1688 |
108
+ | No log | 39.0 | 390 | 1.4706 | 0.1938 |
109
+ | No log | 40.0 | 400 | 1.3595 | 0.1625 |
110
+ | No log | 41.0 | 410 | 1.4236 | 0.1625 |
111
+ | No log | 42.0 | 420 | 1.4180 | 0.1812 |
112
+ | No log | 43.0 | 430 | 1.3993 | 0.1562 |
113
+ | No log | 44.0 | 440 | 1.4066 | 0.1625 |
114
+ | No log | 45.0 | 450 | 1.3760 | 0.175 |
115
+ | No log | 46.0 | 460 | 1.4221 | 0.1812 |
116
+ | No log | 47.0 | 470 | 1.3772 | 0.1625 |
117
+ | No log | 48.0 | 480 | 1.4265 | 0.2 |
118
+ | No log | 49.0 | 490 | 1.4716 | 0.1625 |
119
+ | 0.6962 | 50.0 | 500 | 1.3917 | 0.1625 |
120
 
121
 
122
  ### Framework versions
123
 
124
+ - Transformers 4.33.1
125
+ - Pytorch 2.0.1+cu117
126
  - Datasets 2.14.5
127
  - Tokenizers 0.13.3
config.json CHANGED
@@ -40,5 +40,5 @@
40
  "problem_type": "single_label_classification",
41
  "qkv_bias": true,
42
  "torch_dtype": "float32",
43
- "transformers_version": "4.33.2"
44
  }
 
40
  "problem_type": "single_label_classification",
41
  "qkv_bias": true,
42
  "torch_dtype": "float32",
43
+ "transformers_version": "4.33.1"
44
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aee682d2ef6b87142315630d6bd90626303155b6048b01640bb64a82fcd8e4d
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:996e2f6303ec57de47ff7b46aaf04687ba1b4a4f0d2c342d23955e922816df6c
3
  size 343287149
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51273e105842aa742b7fa69069e302c9cd1fe702ff111c15da1d0ba3be51eca5
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6727b65ac1c11710bc585aebbef0a5e42af550e6e730a2f6d922513c353d2917
3
  size 4027