Hugging Face's logo

uisikdag
/
weeds24_convnext_balanced

Image Classification
Transformers
TensorBoard
Safetensors
convnext
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
uisikdag commited on
Commit
7d482ce
·
verified ·
1 Parent(s): 00daff4

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -16
  2. model.safetensors +1 -1
  3. runs/Oct29_22-45-13_umit-MS-7E07/events.out.tfevents.1730231114.umit-MS-7E07 +2 -2
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9433333333333334
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 [facebook/convnext-large-224](https://huggingface.co/facebook/convnext-large-224) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.1882
37
- - Accuracy: 0.9433
38
 
39
  ## Model description
40
 
@@ -54,11 +54,11 @@ More information needed
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 5e-05
57
- - train_batch_size: 4
58
- - eval_batch_size: 4
59
  - seed: 42
60
  - gradient_accumulation_steps: 4
61
- - total_train_batch_size: 16
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
@@ -68,16 +68,16 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 6.9364 | 1.0 | 150 | 1.5889 | 0.74 |
72
- | 2.3268 | 2.0 | 300 | 0.5301 | 0.8533 |
73
- | 1.2644 | 3.0 | 450 | 0.3337 | 0.9167 |
74
- | 0.91 | 4.0 | 600 | 0.2611 | 0.9067 |
75
- | 0.664 | 5.0 | 750 | 0.2194 | 0.9167 |
76
- | 0.6286 | 6.0 | 900 | 0.2311 | 0.9267 |
77
- | 0.6042 | 7.0 | 1050 | 0.2450 | 0.9233 |
78
- | 0.629 | 8.0 | 1200 | 0.2225 | 0.9333 |
79
- | 0.3318 | 9.0 | 1350 | 0.2032 | 0.9367 |
80
- | 0.2009 | 10.0 | 1500 | 0.1882 | 0.9433 |
81
 
82
 
83
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.94
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 [facebook/convnext-large-224](https://huggingface.co/facebook/convnext-large-224) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.1908
37
+ - Accuracy: 0.94
38
 
39
  ## Model description
40
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 5e-05
57
+ - train_batch_size: 8
58
+ - eval_batch_size: 8
59
  - seed: 42
60
  - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 32
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
 
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 9.0308 | 1.0 | 75 | 2.0854 | 0.5067 |
72
+ | 4.0591 | 2.0 | 150 | 0.9363 | 0.8433 |
73
+ | 1.9789 | 3.0 | 225 | 0.5118 | 0.8867 |
74
+ | 1.3397 | 4.0 | 300 | 0.3700 | 0.9067 |
75
+ | 0.9292 | 5.0 | 375 | 0.2859 | 0.92 |
76
+ | 0.7772 | 6.0 | 450 | 0.2314 | 0.9233 |
77
+ | 0.8323 | 7.0 | 525 | 0.2472 | 0.9233 |
78
+ | 0.7398 | 8.0 | 600 | 0.2647 | 0.9233 |
79
+ | 0.6066 | 9.0 | 675 | 0.2107 | 0.9433 |
80
+ | 0.546 | 10.0 | 750 | 0.1908 | 0.94 |
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6034a786c6a99b725f7c902b8da2cc5757402dcbf98b1fbd13e3a056be946a2e
3
  size 785036472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e950066b3b2eec1d14fdcf8b33114062d32807421e4181b1d3f6730e8242765f
3
  size 785036472
runs/Oct29_22-45-13_umit-MS-7E07/events.out.tfevents.1730231114.umit-MS-7E07 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:918cbbe9ba7314671e3070fa03c3122c788755361e7def44cf50d5565e598991
3
- size 20556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bce76581a9c317bb4df748d88a8daea3cfd83f8a3c83b3e96c87fb09169b8ab
3
+ size 25044