Hugging Face's logo

hansin91
/
emotion_classification

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hansin91 commited on
Commit
f75657e
•
1 Parent(s): f865131

End of training

Browse files
Files changed (2) hide show
  1. README.md +37 -24
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5625
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: 1.3460
36
- - Accuracy: 0.5625
37
 
38
  ## Model description
39
 
@@ -56,34 +56,47 @@ The following hyperparameters were used during training:
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: 20
 
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.8739 | 0.3375 |
68
- | No log | 2.0 | 80 | 1.5652 | 0.4437 |
69
- | No log | 3.0 | 120 | 1.4717 | 0.425 |
70
- | No log | 4.0 | 160 | 1.4022 | 0.4437 |
71
- | No log | 5.0 | 200 | 1.3310 | 0.4625 |
72
- | No log | 6.0 | 240 | 1.2914 | 0.5188 |
73
- | No log | 7.0 | 280 | 1.2637 | 0.4938 |
74
- | No log | 8.0 | 320 | 1.2647 | 0.5375 |
75
- | No log | 9.0 | 360 | 1.2992 | 0.5 |
76
- | No log | 10.0 | 400 | 1.3180 | 0.4625 |
77
- | No log | 11.0 | 440 | 1.2757 | 0.5563 |
78
- | No log | 12.0 | 480 | 1.3529 | 0.5 |
79
- | 1.0866 | 13.0 | 520 | 1.2583 | 0.5625 |
80
- | 1.0866 | 14.0 | 560 | 1.3049 | 0.5375 |
81
- | 1.0866 | 15.0 | 600 | 1.3013 | 0.5312 |
82
- | 1.0866 | 16.0 | 640 | 1.3309 | 0.5312 |
83
- | 1.0866 | 17.0 | 680 | 1.3396 | 0.5687 |
84
- | 1.0866 | 18.0 | 720 | 1.3347 | 0.5062 |
85
- | 1.0866 | 19.0 | 760 | 1.3495 | 0.55 |
86
- | 1.0866 | 20.0 | 800 | 1.3423 | 0.525 |
 
 
 
 
 
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.58125
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: 1.4116
36
+ - Accuracy: 0.5813
37
 
38
  ## Model description
39
 
 
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_steps: 500
64
+ - num_epochs: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 10 | 1.3914 | 0.5312 |
71
+ | No log | 2.0 | 20 | 1.3253 | 0.4875 |
72
+ | No log | 3.0 | 30 | 1.4217 | 0.4813 |
73
+ | No log | 4.0 | 40 | 1.3711 | 0.5062 |
74
+ | No log | 5.0 | 50 | 1.3584 | 0.5 |
75
+ | No log | 6.0 | 60 | 1.3163 | 0.5 |
76
+ | No log | 7.0 | 70 | 1.3824 | 0.5188 |
77
+ | No log | 8.0 | 80 | 1.3882 | 0.525 |
78
+ | No log | 9.0 | 90 | 1.4126 | 0.5188 |
79
+ | No log | 10.0 | 100 | 1.3213 | 0.5625 |
80
+ | No log | 11.0 | 110 | 1.4385 | 0.5 |
81
+ | No log | 12.0 | 120 | 1.3729 | 0.525 |
82
+ | No log | 13.0 | 130 | 1.4603 | 0.4938 |
83
+ | No log | 14.0 | 140 | 1.5326 | 0.4688 |
84
+ | No log | 15.0 | 150 | 1.3687 | 0.5563 |
85
+ | No log | 16.0 | 160 | 1.4537 | 0.55 |
86
+ | No log | 17.0 | 170 | 1.5377 | 0.5188 |
87
+ | No log | 18.0 | 180 | 1.6417 | 0.4688 |
88
+ | No log | 19.0 | 190 | 1.5260 | 0.55 |
89
+ | No log | 20.0 | 200 | 1.6854 | 0.4938 |
90
+ | No log | 21.0 | 210 | 1.6457 | 0.5062 |
91
+ | No log | 22.0 | 220 | 1.5855 | 0.5125 |
92
+ | No log | 23.0 | 230 | 1.5083 | 0.5312 |
93
+ | No log | 24.0 | 240 | 1.5656 | 0.525 |
94
+ | No log | 25.0 | 250 | 1.5931 | 0.5125 |
95
+ | No log | 26.0 | 260 | 1.4351 | 0.5687 |
96
+ | No log | 27.0 | 270 | 1.5031 | 0.525 |
97
+ | No log | 28.0 | 280 | 1.4129 | 0.55 |
98
+ | No log | 29.0 | 290 | 1.5323 | 0.5125 |
99
+ | No log | 30.0 | 300 | 1.5217 | 0.5625 |
100
 
101
 
102
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6030bcafaedfc3ea67113d7f9bb416c629366a56e3c45b35860e94ef53aa7066
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c286ea946c6dfef9f8d6c54196324dd90d53f410a0f84d9d87eb17c40a360104
3
  size 343287149