Hugging Face's logo

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

Image Classification
Transformers
TensorBoard
Safetensors
convnext
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
vlevi commited on
Commit
ca3532f
•
1 Parent(s): 669e644

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -7
  2. model.safetensors +1 -1
  3. runs/Apr06_13-45-13_615cc53a6797/events.out.tfevents.1712411576.615cc53a6797.172.9 +3 -0
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.49640287769784175
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: 1.0272
36
- - Accuracy: 0.4964
37
 
38
  ## Model description
39
 
@@ -61,15 +61,24 @@ 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
- | 1.094 | 0.96 | 19 | 1.0497 | 0.4317 |
71
- | 1.0281 | 1.97 | 39 | 1.0299 | 0.4676 |
72
- | 1.0053 | 2.89 | 57 | 1.0272 | 0.4964 |
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6366906474820144
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: 0.8091
36
+ - Accuracy: 0.6367
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: 12
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.1311 | 0.96 | 19 | 1.0751 | 0.3813 |
71
+ | 1.0477 | 1.97 | 39 | 1.0354 | 0.5036 |
72
+ | 0.9932 | 2.99 | 59 | 1.0054 | 0.5144 |
73
+ | 0.9445 | 4.0 | 79 | 0.9702 | 0.5432 |
74
+ | 0.8911 | 4.96 | 98 | 0.9461 | 0.5647 |
75
+ | 0.8339 | 5.97 | 118 | 0.9079 | 0.5827 |
76
+ | 0.7923 | 6.99 | 138 | 0.8767 | 0.5899 |
77
+ | 0.751 | 8.0 | 158 | 0.8521 | 0.6187 |
78
+ | 0.7222 | 8.96 | 177 | 0.8315 | 0.6223 |
79
+ | 0.688 | 9.97 | 197 | 0.8183 | 0.6259 |
80
+ | 0.6734 | 10.99 | 217 | 0.8091 | 0.6367 |
81
+ | 0.6734 | 11.54 | 228 | 0.8090 | 0.6331 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a96f406cfd0c835466b0b3692dcb3ba80a0dcdd0d4b69b24bc8d5275f9423852
3
  size 111311004
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38806f09cbe1f816a290a2710903d15a2acfdd321c947908b1a7dea2fa2f9c7e
3
  size 111311004
runs/Apr06_13-45-13_615cc53a6797/events.out.tfevents.1712411576.615cc53a6797.172.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1794aeb54af6b51701937836217ac9a5d026cb19bdaab38c3e341e19dd20896
3
+ size 411