Hugging Face's logo

kazuma313
/
emotion_classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
kazuma313 commited on
Commit
75b81e0
·
verified ·
1 Parent(s): 6ac2911

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -10
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5375
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: 1.3293
36
- - Accuracy: 0.5375
37
 
38
  ## Model description
39
 
@@ -58,17 +58,27 @@ 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: linear
61
- - num_epochs: 5
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 20 | 1.4818 | 0.4375 |
68
- | No log | 2.0 | 40 | 1.4215 | 0.4562 |
69
- | No log | 3.0 | 60 | 1.3947 | 0.5 |
70
- | No log | 4.0 | 80 | 1.3840 | 0.5 |
71
- | No log | 5.0 | 100 | 1.3293 | 0.5375 |
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
@@ -76,4 +86,4 @@ The following hyperparameters were used during training:
76
  - Transformers 4.35.2
77
  - Pytorch 2.1.0+cu121
78
  - Datasets 2.17.0
79
- - Tokenizers 0.15.1
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.56875
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: 1.1901
36
+ - Accuracy: 0.5687
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: linear
61
+ - num_epochs: 15
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 20 | 1.9937 | 0.225 |
68
+ | No log | 2.0 | 40 | 1.7466 | 0.4188 |
69
+ | No log | 3.0 | 60 | 1.5370 | 0.5375 |
70
+ | No log | 4.0 | 80 | 1.4797 | 0.5125 |
71
+ | No log | 5.0 | 100 | 1.3531 | 0.55 |
72
+ | No log | 6.0 | 120 | 1.3115 | 0.5687 |
73
+ | No log | 7.0 | 140 | 1.2982 | 0.5375 |
74
+ | No log | 8.0 | 160 | 1.2543 | 0.5437 |
75
+ | No log | 9.0 | 180 | 1.2666 | 0.525 |
76
+ | No log | 10.0 | 200 | 1.2427 | 0.5312 |
77
+ | No log | 11.0 | 220 | 1.2100 | 0.5687 |
78
+ | No log | 12.0 | 240 | 1.2494 | 0.5375 |
79
+ | No log | 13.0 | 260 | 1.2266 | 0.5625 |
80
+ | No log | 14.0 | 280 | 1.2360 | 0.5437 |
81
+ | No log | 15.0 | 300 | 1.1901 | 0.5687 |
82
 
83
 
84
  ### Framework versions
 
86
  - Transformers 4.35.2
87
  - Pytorch 2.1.0+cu121
88
  - Datasets 2.17.0
89
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4a2e0d540bc0324540c1cb984b7c0a1c76fa01cc0cd36a4bc31a911c68ad446
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42ec946cc0481cd3022c43814e375329d6d30af0278f0f194875eaba6576181
3
  size 343242432