Hugging Face's logo

firedfrog
/
convnext-tiny-224-finetuned-eurosat-albumentations

Image Classification
Transformers
TensorBoard
Safetensors
convnext
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
firedfrog commited on
Commit
8571d4d
•
1 Parent(s): a89cfaf

End of training

Browse files
Files changed (3) hide show
  1. README.md +54 -7
  2. model.safetensors +1 -1
  3. runs/Jun04_03-53-41_fdd1623eec49/events.out.tfevents.1717473813.fdd1623eec49.1298.1 +3 -0
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.08125
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 [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.0736
36
- - Accuracy: 0.0813
37
 
38
  ## Model description
39
 
@@ -61,15 +61,62 @@ The following hyperparameters were used during training:
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: 3
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 1.0 | 5 | 2.0870 | 0.0688 |
71
- | 2.067 | 2.0 | 10 | 2.0736 | 0.0813 |
72
- | 2.067 | 3.0 | 15 | 2.0695 | 0.0813 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.5
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 [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.3086
36
+ - Accuracy: 0.5
37
 
38
  ## Model description
39
 
 
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: 50
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 5 | 2.0663 | 0.1562 |
71
+ | 2.0637 | 2.0 | 10 | 2.0571 | 0.1812 |
72
+ | 2.0637 | 3.0 | 15 | 2.0389 | 0.1938 |
73
+ | 2.0295 | 4.0 | 20 | 2.0109 | 0.2437 |
74
+ | 2.0295 | 5.0 | 25 | 1.9754 | 0.2875 |
75
+ | 1.9452 | 6.0 | 30 | 1.9335 | 0.2938 |
76
+ | 1.9452 | 7.0 | 35 | 1.8869 | 0.275 |
77
+ | 1.8289 | 8.0 | 40 | 1.8378 | 0.2812 |
78
+ | 1.8289 | 9.0 | 45 | 1.7800 | 0.3563 |
79
+ | 1.7075 | 10.0 | 50 | 1.7231 | 0.3563 |
80
+ | 1.7075 | 11.0 | 55 | 1.6730 | 0.3625 |
81
+ | 1.5909 | 12.0 | 60 | 1.6253 | 0.3688 |
82
+ | 1.5909 | 13.0 | 65 | 1.5897 | 0.3875 |
83
+ | 1.4997 | 14.0 | 70 | 1.5604 | 0.4 |
84
+ | 1.4997 | 15.0 | 75 | 1.5336 | 0.425 |
85
+ | 1.4066 | 16.0 | 80 | 1.5147 | 0.425 |
86
+ | 1.4066 | 17.0 | 85 | 1.4923 | 0.425 |
87
+ | 1.3344 | 18.0 | 90 | 1.4744 | 0.4375 |
88
+ | 1.3344 | 19.0 | 95 | 1.4615 | 0.4437 |
89
+ | 1.2545 | 20.0 | 100 | 1.4479 | 0.4437 |
90
+ | 1.2545 | 21.0 | 105 | 1.4311 | 0.45 |
91
+ | 1.1789 | 22.0 | 110 | 1.4222 | 0.475 |
92
+ | 1.1789 | 23.0 | 115 | 1.4099 | 0.4813 |
93
+ | 1.1186 | 24.0 | 120 | 1.3926 | 0.4688 |
94
+ | 1.1186 | 25.0 | 125 | 1.3835 | 0.4625 |
95
+ | 1.0685 | 26.0 | 130 | 1.3747 | 0.4625 |
96
+ | 1.0685 | 27.0 | 135 | 1.3622 | 0.4625 |
97
+ | 0.9935 | 28.0 | 140 | 1.3523 | 0.4688 |
98
+ | 0.9935 | 29.0 | 145 | 1.3514 | 0.45 |
99
+ | 0.9453 | 30.0 | 150 | 1.3413 | 0.4688 |
100
+ | 0.9453 | 31.0 | 155 | 1.3334 | 0.45 |
101
+ | 0.9162 | 32.0 | 160 | 1.3239 | 0.45 |
102
+ | 0.9162 | 33.0 | 165 | 1.3177 | 0.475 |
103
+ | 0.8637 | 34.0 | 170 | 1.3090 | 0.475 |
104
+ | 0.8637 | 35.0 | 175 | 1.3078 | 0.4938 |
105
+ | 0.8298 | 36.0 | 180 | 1.3086 | 0.5 |
106
+ | 0.8298 | 37.0 | 185 | 1.2990 | 0.5 |
107
+ | 0.7801 | 38.0 | 190 | 1.2975 | 0.4938 |
108
+ | 0.7801 | 39.0 | 195 | 1.2946 | 0.4938 |
109
+ | 0.7691 | 40.0 | 200 | 1.2921 | 0.4875 |
110
+ | 0.7691 | 41.0 | 205 | 1.2913 | 0.4938 |
111
+ | 0.7409 | 42.0 | 210 | 1.2902 | 0.4875 |
112
+ | 0.7409 | 43.0 | 215 | 1.2886 | 0.4875 |
113
+ | 0.7223 | 44.0 | 220 | 1.2860 | 0.4938 |
114
+ | 0.7223 | 45.0 | 225 | 1.2849 | 0.4875 |
115
+ | 0.7091 | 46.0 | 230 | 1.2849 | 0.4875 |
116
+ | 0.7091 | 47.0 | 235 | 1.2854 | 0.4875 |
117
+ | 0.6915 | 48.0 | 240 | 1.2845 | 0.4875 |
118
+ | 0.6915 | 49.0 | 245 | 1.2842 | 0.4875 |
119
+ | 0.6917 | 50.0 | 250 | 1.2840 | 0.4875 |
120
 
121
 
122
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc1dd1d24993c02e701c73da488ed00a278bc39c39a6509116724392831d3287
3
  size 111326392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d30ff755d67093e2e4428e883ff2e600541d1a82ac2cd7a95f33877447bc51
3
  size 111326392
runs/Jun04_03-53-41_fdd1623eec49/events.out.tfevents.1717473813.fdd1623eec49.1298.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:596ab661a2d1f14d6f9c88e7c6b56e9312e119cab4a409217155816f3d00687d
3
+ size 411