Hugging Face's logo

karim155
/
convnext-tiny-224-finetuned

Image Classification
Transformers
TensorBoard
Safetensors
convnext
Generated from Trainer
Model card Files
xet
 Metrics Community
karim155 commited on
Commit
cd84a33
·
verified ·
1 Parent(s): 83a128e

Model save

Browse files
Files changed (1) hide show
  1. README.md +21 -11
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.8063
21
- - Logloss: 0.8063
22
- - Accuracy: {'accuracy': 0.668}
23
 
24
  ## Model description
25
 
@@ -47,17 +47,27 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
- - num_epochs: 5
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy |
55
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------------------:|
56
- | 1.1408 | 0.992 | 31 | 1.0801 | 1.0801 | {'accuracy': 0.537} |
57
- | 0.9476 | 1.984 | 62 | 0.9146 | 0.9146 | {'accuracy': 0.621} |
58
- | 0.8816 | 2.976 | 93 | 0.8400 | 0.8400 | {'accuracy': 0.655} |
59
- | 0.8156 | 4.0 | 125 | 0.8113 | 0.8113 | {'accuracy': 0.663} |
60
- | 0.8013 | 4.96 | 155 | 0.8063 | 0.8063 | {'accuracy': 0.668} |
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.2328
21
+ - Logloss: 1.2328
22
+ - Accuracy: {'accuracy': 0.5220588235294118}
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 15
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Logloss | Accuracy |
55
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|:---------------------------------:|
56
+ | No log | 0.9412 | 8 | 1.6104 | 1.6104 | {'accuracy': 0.2426470588235294} |
57
+ | 1.6172 | 2.0 | 17 | 1.5560 | 1.5560 | {'accuracy': 0.2867647058823529} |
58
+ | 1.5532 | 2.9412 | 25 | 1.5107 | 1.5107 | {'accuracy': 0.36764705882352944} |
59
+ | 1.4806 | 4.0 | 34 | 1.4612 | 1.4612 | {'accuracy': 0.40441176470588236} |
60
+ | 1.4041 | 4.9412 | 42 | 1.4208 | 1.4208 | {'accuracy': 0.43014705882352944} |
61
+ | 1.3407 | 6.0 | 51 | 1.3774 | 1.3774 | {'accuracy': 0.4632352941176471} |
62
+ | 1.3407 | 6.9412 | 59 | 1.3422 | 1.3422 | {'accuracy': 0.45588235294117646} |
63
+ | 1.2852 | 8.0 | 68 | 1.3110 | 1.3110 | {'accuracy': 0.47058823529411764} |
64
+ | 1.2272 | 8.9412 | 76 | 1.2849 | 1.2849 | {'accuracy': 0.49264705882352944} |
65
+ | 1.1841 | 10.0 | 85 | 1.2634 | 1.2634 | {'accuracy': 0.5073529411764706} |
66
+ | 1.1625 | 10.9412 | 93 | 1.2540 | 1.2540 | {'accuracy': 0.49264705882352944} |
67
+ | 1.1166 | 12.0 | 102 | 1.2423 | 1.2423 | {'accuracy': 0.5147058823529411} |
68
+ | 1.1079 | 12.9412 | 110 | 1.2351 | 1.2351 | {'accuracy': 0.5257352941176471} |
69
+ | 1.1079 | 14.0 | 119 | 1.2328 | 1.2328 | {'accuracy': 0.5220588235294118} |
70
+ | 1.0974 | 14.1176 | 120 | 1.2328 | 1.2328 | {'accuracy': 0.5220588235294118} |
71
 
72
 
73
  ### Framework versions