Hugging Face's logo

CVPROJ25
/
FINETUNED

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Model card Files
xet
 Community
agarwali commited on
Commit
86bd01c
·
verified ·
1 Parent(s): ed881b7

Training complete

Browse files
Files changed (2) hide show
  1. README.md +14 -12
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.9199
22
- - Accuracy: 0.774
23
 
24
  ## Model description
25
 
@@ -39,10 +39,10 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
- - train_batch_size: 512
43
- - eval_batch_size: 16
44
  - seed: 42
45
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - num_epochs: 10
48
  - mixed_precision_training: Native AMP
@@ -51,14 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 0.8241 | 1.0 | 16 | 0.8922 | 0.773 |
55
- | 0.3997 | 2.0 | 32 | 0.9019 | 0.7705 |
56
- | 0.2905 | 3.0 | 48 | 0.9199 | 0.774 |
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
- - Transformers 5.2.0
62
- - Pytorch 2.5.1
63
- - Datasets 4.6.1
64
- - Tokenizers 0.22.1
 
18
 
19
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6934
22
+ - Accuracy: 0.5
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
+ - train_batch_size: 256
43
+ - eval_batch_size: 8
44
  - seed: 42
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - num_epochs: 10
48
  - mixed_precision_training: Native AMP
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | No log | 1.0 | 1 | 0.7093 | 0.5 |
55
+ | No log | 2.0 | 2 | 0.6849 | 0.5 |
56
+ | No log | 3.0 | 3 | 0.6804 | 0.5 |
57
+ | No log | 4.0 | 4 | 0.6861 | 0.5 |
58
+ | No log | 5.0 | 5 | 0.6934 | 0.5 |
59
 
60
 
61
  ### Framework versions
62
 
63
+ - Transformers 5.0.0
64
+ - Pytorch 2.10.0+cu128
65
+ - Datasets 4.0.0
66
+ - Tokenizers 0.22.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09d8c13da6fc8f3864dc1e4f9d37dbc37b1ee5fa25aac6b822a1d00236a31b10
3
  size 346293856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4058f2e18337c5a7189d81af59b12a84b49757c268e989c696082ae1ac0e85e4
3
  size 346293856