Hugging Face's logo

SoulPerforms
/
visual_emotion_classification_vit_base_finetunned

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
SoulPerforms commited on
Commit
77ef799
•
1 Parent(s): fc96bdc

End of training

Browse files
Files changed (5) hide show
  1. README.md +15 -37
  2. model.safetensors +1 -1
  3. runs/Feb11_14-18-43_47112c2db62a/events.out.tfevents.1707661156.47112c2db62a.1339.0 +3 -0
  4. runs/Feb11_14-18-43_47112c2db62a/events.out.tfevents.1707661310.47112c2db62a.1339.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5125
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: 1.3576
36
- - Accuracy: 0.5125
37
 
38
  ## Model description
39
 
@@ -52,48 +52,26 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 2.5e-05
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: 30
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.9700 | 0.2625 |
68
- | 2.0074 | 2.0 | 80 | 1.7194 | 0.3688 |
69
- | 1.726 | 3.0 | 120 | 1.5775 | 0.3875 |
70
- | 1.5202 | 4.0 | 160 | 1.4900 | 0.4875 |
71
- | 1.3857 | 5.0 | 200 | 1.4261 | 0.4938 |
72
- | 1.3857 | 6.0 | 240 | 1.4090 | 0.5 |
73
- | 1.2831 | 7.0 | 280 | 1.3510 | 0.475 |
74
- | 1.2007 | 8.0 | 320 | 1.3788 | 0.475 |
75
- | 1.1256 | 9.0 | 360 | 1.3183 | 0.5 |
76
- | 1.0345 | 10.0 | 400 | 1.2937 | 0.4813 |
77
- | 1.0345 | 11.0 | 440 | 1.2384 | 0.5437 |
78
- | 0.9438 | 12.0 | 480 | 1.2100 | 0.525 |
79
- | 0.872 | 13.0 | 520 | 1.2450 | 0.525 |
80
- | 0.8193 | 14.0 | 560 | 1.2264 | 0.5312 |
81
- | 0.763 | 15.0 | 600 | 1.2296 | 0.5125 |
82
- | 0.763 | 16.0 | 640 | 1.2539 | 0.5188 |
83
- | 0.7166 | 17.0 | 680 | 1.2253 | 0.5563 |
84
- | 0.6328 | 18.0 | 720 | 1.2723 | 0.5312 |
85
- | 0.5917 | 19.0 | 760 | 1.2870 | 0.4875 |
86
- | 0.5841 | 20.0 | 800 | 1.3011 | 0.5375 |
87
- | 0.5841 | 21.0 | 840 | 1.2071 | 0.575 |
88
- | 0.559 | 22.0 | 880 | 1.2555 | 0.575 |
89
- | 0.5109 | 23.0 | 920 | 1.3140 | 0.5 |
90
- | 0.5036 | 24.0 | 960 | 1.2593 | 0.5 |
91
- | 0.4787 | 25.0 | 1000 | 1.2573 | 0.5813 |
92
- | 0.4787 | 26.0 | 1040 | 1.2163 | 0.55 |
93
- | 0.4583 | 27.0 | 1080 | 1.2349 | 0.5563 |
94
- | 0.4766 | 28.0 | 1120 | 1.3349 | 0.5188 |
95
- | 0.4709 | 29.0 | 1160 | 1.3284 | 0.5312 |
96
- | 0.4442 | 30.0 | 1200 | 1.2684 | 0.5625 |
97
 
98
 
99
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.525
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: 1.3848
36
+ - Accuracy: 0.525
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: 8
57
+ - eval_batch_size: 8
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
+ | 2.0383 | 0.62 | 50 | 1.9425 | 0.2875 |
68
+ | 1.7682 | 1.25 | 100 | 1.6311 | 0.3875 |
69
+ | 1.6002 | 1.88 | 150 | 1.5707 | 0.425 |
70
+ | 1.413 | 2.5 | 200 | 1.4598 | 0.5 |
71
+ | 1.3389 | 3.12 | 250 | 1.3674 | 0.5875 |
72
+ | 1.2695 | 3.75 | 300 | 1.3950 | 0.525 |
73
+ | 1.1953 | 4.38 | 350 | 1.3466 | 0.5563 |
74
+ | 1.1615 | 5.0 | 400 | 1.3819 | 0.5062 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceaeedcda1244e5ecdb8e968b266527d9fb7687468430639b3063a4cb92ef017
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1c0fd095ba02d87c40fb8bc0023bc3cdb2fc593e1d6e9765a1f8e47f1132cf
3
  size 343242432
runs/Feb11_14-18-43_47112c2db62a/events.out.tfevents.1707661156.47112c2db62a.1339.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d5da27e70ae8cbe556f5c408a42018445c11a2ded0a2f30a223f6a7ded64a1
3
+ size 8720
runs/Feb11_14-18-43_47112c2db62a/events.out.tfevents.1707661310.47112c2db62a.1339.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2adf613b7982916b9c29a952c626e58504844e19b4fc60ab5bf877646ad508
3
+ size 411
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4c4f9a56ab9811363ac442944399a06f8b4bde3fb981dc9c173b021a1be7589
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238af52eff85946b6e3a7785fb0c11babe1890bb5a64cb54a37b65143c8fc944
3
  size 4664