Hugging Face's logo

canadianjosieharrison
/
swinv2-large-patch4-window12-192-22k-augmented

Image Classification
Transformers
Safetensors
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
canadianjosieharrison commited on
Commit
2bfafee
•
1 Parent(s): f9f77ba

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -12
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8439716312056738
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 [microsoft/swinv2-large-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-large-patch4-window12-192-22k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4230
36
- - Accuracy: 0.8440
37
 
38
  ## Model description
39
 
@@ -53,25 +53,29 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0001
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 8
60
- - total_train_batch_size: 256
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: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 1.0 | 5 | 0.8342 | 0.7447 |
71
- | 1.3135 | 2.0 | 10 | 0.6567 | 0.7872 |
72
- | 1.3135 | 3.0 | 15 | 0.4849 | 0.8227 |
73
- | 0.4762 | 4.0 | 20 | 0.4877 | 0.8440 |
74
- | 0.4762 | 5.0 | 25 | 0.4230 | 0.8440 |
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8723404255319149
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 [microsoft/swinv2-large-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-large-patch4-window12-192-22k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3067
36
+ - Accuracy: 0.8723
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0001
56
+ - train_batch_size: 48
57
+ - eval_batch_size: 48
58
  - seed: 42
59
  - gradient_accumulation_steps: 8
60
+ - total_train_batch_size: 384
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: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.89 | 3 | 1.4847 | 0.5816 |
71
+ | No log | 1.78 | 6 | 0.9256 | 0.6950 |
72
+ | 1.2457 | 2.96 | 10 | 0.6017 | 0.7589 |
73
+ | 1.2457 | 3.85 | 13 | 0.3806 | 0.8723 |
74
+ | 1.2457 | 4.74 | 16 | 0.3866 | 0.8440 |
75
+ | 0.3656 | 5.93 | 20 | 0.3358 | 0.8794 |
76
+ | 0.3656 | 6.81 | 23 | 0.2803 | 0.8865 |
77
+ | 0.3656 | 8.0 | 27 | 0.3079 | 0.8723 |
78
+ | 0.2205 | 8.89 | 30 | 0.3067 | 0.8723 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e17ac7c735a9160c2c9e7c6ab486ac1471de2415cbb9d6dcd54db17f27ecaa9
3
  size 780923176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b34b2dc5688dc464a90281c6f9de3342c86072d7e1978c5f60e0753085d5b9
3
  size 780923176