Hugging Face's logo

ruben09
/
emotion_classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ruben09 commited on
Commit
b3e7242
•
1 Parent(s): 00ad6fc

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -44
  2. runs/Sep06_16-25-30_ae5ec11cb08b/events.out.tfevents.1725639936.ae5ec11cb08b.394.4 +2 -2
  3. runs/Sep06_16-25-30_ae5ec11cb08b/events.out.tfevents.1725640737.ae5ec11cb08b.394.5 +3 -0
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.55625
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 1.2963
37
- - Accuracy: 0.5563
38
 
39
  ## Model description
40
 
@@ -62,52 +62,32 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: cosine_with_restarts
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 40
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 2.0771 | 1.0 | 10 | 2.0698 | 0.1375 |
72
- | 2.0613 | 2.0 | 20 | 2.0368 | 0.2875 |
73
- | 2.0214 | 3.0 | 30 | 2.0010 | 0.2625 |
74
- | 1.9314 | 4.0 | 40 | 1.8913 | 0.3 |
75
- | 1.785 | 5.0 | 50 | 1.7270 | 0.375 |
76
- | 1.6343 | 6.0 | 60 | 1.6009 | 0.4313 |
77
- | 1.5327 | 7.0 | 70 | 1.5766 | 0.3937 |
78
- | 1.452 | 8.0 | 80 | 1.4714 | 0.475 |
79
- | 1.38 | 9.0 | 90 | 1.4570 | 0.4688 |
80
- | 1.3061 | 10.0 | 100 | 1.4357 | 0.4688 |
81
- | 1.2331 | 11.0 | 110 | 1.3691 | 0.4938 |
82
- | 1.1784 | 12.0 | 120 | 1.3377 | 0.4813 |
83
- | 1.1049 | 13.0 | 130 | 1.2982 | 0.5625 |
84
- | 1.0938 | 14.0 | 140 | 1.2847 | 0.5188 |
85
- | 1.0191 | 15.0 | 150 | 1.2630 | 0.575 |
86
- | 0.9665 | 16.0 | 160 | 1.3427 | 0.4938 |
87
- | 0.9028 | 17.0 | 170 | 1.3189 | 0.525 |
88
- | 0.886 | 18.0 | 180 | 1.2599 | 0.5312 |
89
- | 0.8272 | 19.0 | 190 | 1.3148 | 0.525 |
90
- | 0.7923 | 20.0 | 200 | 1.2634 | 0.55 |
91
- | 0.8033 | 21.0 | 210 | 1.2664 | 0.5625 |
92
- | 0.724 | 22.0 | 220 | 1.2286 | 0.525 |
93
- | 0.6966 | 23.0 | 230 | 1.3408 | 0.5375 |
94
- | 0.6722 | 24.0 | 240 | 1.3032 | 0.5062 |
95
- | 0.6816 | 25.0 | 250 | 1.3318 | 0.5062 |
96
- | 0.6162 | 26.0 | 260 | 1.3775 | 0.4938 |
97
- | 0.6099 | 27.0 | 270 | 1.2903 | 0.5437 |
98
- | 0.5786 | 28.0 | 280 | 1.2361 | 0.6 |
99
- | 0.5931 | 29.0 | 290 | 1.2998 | 0.5312 |
100
- | 0.5849 | 30.0 | 300 | 1.3221 | 0.5062 |
101
- | 0.5606 | 31.0 | 310 | 1.2756 | 0.5125 |
102
- | 0.5561 | 32.0 | 320 | 1.3732 | 0.4813 |
103
- | 0.547 | 33.0 | 330 | 1.3308 | 0.5375 |
104
- | 0.5405 | 34.0 | 340 | 1.3506 | 0.5062 |
105
- | 0.5419 | 35.0 | 350 | 1.2487 | 0.5625 |
106
- | 0.5168 | 36.0 | 360 | 1.2269 | 0.525 |
107
- | 0.5361 | 37.0 | 370 | 1.2993 | 0.55 |
108
- | 0.5375 | 38.0 | 380 | 1.2806 | 0.575 |
109
- | 0.5235 | 39.0 | 390 | 1.3404 | 0.5188 |
110
- | 0.5318 | 40.0 | 400 | 1.3315 | 0.4938 |
111
 
112
 
113
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.56875
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.2493
37
+ - Accuracy: 0.5687
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: cosine_with_restarts
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 20
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 2.0679 | 1.0 | 10 | 2.0574 | 0.175 |
72
+ | 2.0366 | 2.0 | 20 | 2.0083 | 0.2812 |
73
+ | 1.9469 | 3.0 | 30 | 1.9119 | 0.35 |
74
+ | 1.8166 | 4.0 | 40 | 1.7702 | 0.4125 |
75
+ | 1.6821 | 5.0 | 50 | 1.6176 | 0.45 |
76
+ | 1.5587 | 6.0 | 60 | 1.5747 | 0.425 |
77
+ | 1.4703 | 7.0 | 70 | 1.4444 | 0.5375 |
78
+ | 1.4032 | 8.0 | 80 | 1.4226 | 0.5312 |
79
+ | 1.3367 | 9.0 | 90 | 1.3937 | 0.5188 |
80
+ | 1.2889 | 10.0 | 100 | 1.3186 | 0.5375 |
81
+ | 1.2136 | 11.0 | 110 | 1.3313 | 0.55 |
82
+ | 1.1745 | 12.0 | 120 | 1.3027 | 0.5312 |
83
+ | 1.1477 | 13.0 | 130 | 1.3004 | 0.5375 |
84
+ | 1.1414 | 14.0 | 140 | 1.2442 | 0.55 |
85
+ | 1.1202 | 15.0 | 150 | 1.2957 | 0.5062 |
86
+ | 1.0923 | 16.0 | 160 | 1.3045 | 0.5125 |
87
+ | 1.0765 | 17.0 | 170 | 1.2533 | 0.5563 |
88
+ | 1.0678 | 18.0 | 180 | 1.2392 | 0.5437 |
89
+ | 1.0837 | 19.0 | 190 | 1.2750 | 0.5375 |
90
+ | 1.0562 | 20.0 | 200 | 1.2275 | 0.5625 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
 
92
 
93
  ### Framework versions
runs/Sep06_16-25-30_ae5ec11cb08b/events.out.tfevents.1725639936.ae5ec11cb08b.394.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4d4d122774b094c22072692d50c2a2ad978fead2eea3c22f2ec94f201b4ec66
3
- size 15414
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e415de98e3d2f8fe2027ea9e25fb41c563dfa4b77015c707fb2ad86810ab1443
3
+ size 16091
runs/Sep06_16-25-30_ae5ec11cb08b/events.out.tfevents.1725640737.ae5ec11cb08b.394.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2253a016af823d211e7df00b25df59778e36f7f86bd431dfe625cb0434dee10a
3
+ size 411