Hugging Face's logo

anggtpd
/
emotion_recognition

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
anggtpd commited on
Commit
69c080b
•
1 Parent(s): 9474068

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -12
  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: 0.34375
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: 1.7721
36
- - Accuracy: 0.3438
37
 
38
  ## Model description
39
 
@@ -53,25 +53,30 @@ More information needed
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: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.078 | 1.0 | 10 | 2.0567 | 0.1875 |
71
- | 1.9889 | 2.0 | 20 | 1.9714 | 0.2812 |
72
- | 1.874 | 3.0 | 30 | 1.8689 | 0.3312 |
73
- | 1.7814 | 4.0 | 40 | 1.8008 | 0.3812 |
74
- | 1.7228 | 5.0 | 50 | 1.7661 | 0.4 |
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.45625
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: 1.6139
36
+ - Accuracy: 0.4562
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
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: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 5 | 1.9416 | 0.3438 |
71
+ | 1.8445 | 2.0 | 10 | 1.8517 | 0.3937 |
72
+ | 1.8445 | 3.0 | 15 | 1.7436 | 0.3875 |
73
+ | 1.6748 | 4.0 | 20 | 1.6654 | 0.475 |
74
+ | 1.6748 | 5.0 | 25 | 1.6098 | 0.5062 |
75
+ | 1.5405 | 6.0 | 30 | 1.5734 | 0.4875 |
76
+ | 1.5405 | 7.0 | 35 | 1.5446 | 0.4938 |
77
+ | 1.4603 | 8.0 | 40 | 1.5415 | 0.4938 |
78
+ | 1.4603 | 9.0 | 45 | 1.5173 | 0.5062 |
79
+ | 1.4154 | 10.0 | 50 | 1.4983 | 0.5062 |
80
 
81
 
82
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78374219fc86014cbe48922dba8161795f350c83a7637d3113531e7068cd9092
3
  size 343284397
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe66e0a84467c3897a72f7e4c56f2c5d729550357b49cd482ac0602d3160934c
3
  size 343284397