Hugging Face's logo

bluebird089
/
test-vit

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
bluebird089 commited on
Commit
92bc685
•
1 Parent(s): baf0840

End of training

Browse files
Files changed (3) hide show
  1. README.md +13 -14
  2. model.safetensors +1 -1
  3. runs/Mar22_08-14-34_8d18874f154f/events.out.tfevents.1711095278.8d18874f154f.4773.1 +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4068
21
- - Accuracy: 0.9909
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
41
  - train_batch_size: 64
42
  - eval_batch_size: 64
43
  - seed: 42
@@ -46,22 +46,21 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 11
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | No log | 0.84 | 4 | 1.3347 | 0.9027 |
56
- | No log | 1.89 | 9 | 1.0340 | 0.9605 |
57
- | 1.2661 | 2.95 | 14 | 0.8152 | 0.9696 |
58
- | 1.2661 | 4.0 | 19 | 0.6598 | 0.9878 |
59
- | 0.7865 | 4.84 | 23 | 0.5723 | 0.9878 |
60
- | 0.7865 | 5.89 | 28 | 0.4964 | 0.9909 |
61
- | 0.5287 | 6.95 | 33 | 0.4474 | 0.9909 |
62
- | 0.5287 | 8.0 | 38 | 0.4200 | 0.9939 |
63
- | 0.4142 | 8.84 | 42 | 0.4085 | 0.9909 |
64
- | 0.4142 | 9.26 | 44 | 0.4068 | 0.9909 |
65
 
66
 
67
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2285
21
+ - Accuracy: 0.9970
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 6e-05
41
  - train_batch_size: 64
42
  - eval_batch_size: 64
43
  - seed: 42
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | No log | 0.84 | 4 | 0.7136 | 0.9909 |
56
+ | No log | 1.89 | 9 | 0.4919 | 0.9939 |
57
+ | 0.6427 | 2.95 | 14 | 0.3749 | 0.9970 |
58
+ | 0.6427 | 4.0 | 19 | 0.3094 | 0.9939 |
59
+ | 0.3516 | 4.84 | 23 | 0.2767 | 0.9970 |
60
+ | 0.3516 | 5.89 | 28 | 0.2496 | 0.9970 |
61
+ | 0.2484 | 6.95 | 33 | 0.2357 | 0.9970 |
62
+ | 0.2484 | 8.0 | 38 | 0.2295 | 0.9970 |
63
+ | 0.2147 | 8.42 | 40 | 0.2285 | 0.9970 |
 
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3838d23df6cec363811f78a8140de7e580221df6708c291e5ddbd13b941ba6b1
3
  size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f54ade7e46516dae93bf8fc3323b1f07f63e1deec2a560b0cef8f0ce9758d1
3
  size 343236280
runs/Mar22_08-14-34_8d18874f154f/events.out.tfevents.1711095278.8d18874f154f.4773.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:457710f7bc9e037b718f626b86700fc85bf6101e1a00858f4e45d17bd80582a9
3
- size 7998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05891149953a2dd15820168aa9f5b5db473744d9b007ff3084093555d41c5a0f
3
+ size 8870