Hugging Face's logo

hemakumari
/
vit-base-patch16-224-in21k-finetune

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hemakumari commited on
Commit
456fdb7
•
1 Parent(s): c0e4acd

Model save

Browse files
Files changed (3) hide show
  1. README.md +9 -7
  2. model.safetensors +1 -1
  3. runs/Mar13_08-01-19_83e1a6899153/events.out.tfevents.1710316897.83e1a6899153.35.4 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.3103448275862069
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the image_folder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.6070
36
- - Accuracy: 0.3103
37
 
38
  ## Model description
39
 
@@ -61,15 +61,17 @@ 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
- | No log | 0.92 | 3 | 1.6164 | 0.2644 |
71
- | No log | 1.85 | 6 | 1.6094 | 0.2989 |
72
- | No log | 2.77 | 9 | 1.6070 | 0.3103 |
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.22988505747126436
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the image_folder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.6043
36
+ - Accuracy: 0.2299
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: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.92 | 3 | 1.6377 | 0.0920 |
71
+ | No log | 1.85 | 6 | 1.6208 | 0.1954 |
72
+ | No log | 2.77 | 9 | 1.6120 | 0.2184 |
73
+ | 1.5539 | 4.0 | 13 | 1.6054 | 0.2299 |
74
+ | 1.5539 | 4.62 | 15 | 1.6043 | 0.2299 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe54445c4ec602e0423cd9c044ba7720c81f213b4b135dae1cb51bb113eac8a
3
  size 343233204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0f886901993d0a4f33eb9dcae38498850bf94579c5925dc1b22064d7776b62
3
  size 343233204
runs/Mar13_08-01-19_83e1a6899153/events.out.tfevents.1710316897.83e1a6899153.35.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e66d7980049358a70bb48093826febe4c7e1324a814079e0bbb47e16014fba8
3
- size 6576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fcb163105b13502a7e7343e7dcfcac9ef37a7a42ad589e0b60106af14b694d5
3
+ size 6924