Hugging Face's logo

onizukal
/
Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-large-patch16_fold1

Image Classification
Transformers
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
onizukal commited on
Commit
af9dea5
•
1 Parent(s): eec2e54

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -26
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6201466196035841
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/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 3.7539
36
- - Accuracy: 0.6201
37
 
38
  ## Model description
39
 
@@ -59,32 +59,22 @@ The following hyperparameters were used during training:
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
- - num_epochs: 20
63
 
64
  ### Training results
65
 
66
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
- | 1.3484 | 1.0 | 924 | 1.3605 | 0.5327 |
69
- | 1.1536 | 2.0 | 1848 | 1.2783 | 0.5515 |
70
- | 1.1327 | 3.0 | 2772 | 1.1624 | 0.6071 |
71
- | 0.7516 | 4.0 | 3696 | 1.2618 | 0.5952 |
72
- | 0.5923 | 5.0 | 4620 | 1.4123 | 0.6022 |
73
- | 0.5275 | 6.0 | 5544 | 1.5876 | 0.5927 |
74
- | 0.3529 | 7.0 | 6468 | 1.7994 | 0.5887 |
75
- | 0.2628 | 8.0 | 7392 | 1.9375 | 0.5984 |
76
- | 0.2774 | 9.0 | 8316 | 2.3876 | 0.5889 |
77
- | 0.1651 | 10.0 | 9240 | 2.6650 | 0.5873 |
78
- | 0.1728 | 11.0 | 10164 | 2.8556 | 0.5867 |
79
- | 0.028 | 12.0 | 11088 | 3.0398 | 0.6003 |
80
- | 0.0023 | 13.0 | 12012 | 3.3114 | 0.6044 |
81
- | 0.0042 | 14.0 | 12936 | 3.3149 | 0.6082 |
82
- | 0.0192 | 15.0 | 13860 | 3.4661 | 0.6028 |
83
- | 0.0004 | 16.0 | 14784 | 3.5853 | 0.6058 |
84
- | 0.0363 | 17.0 | 15708 | 3.5853 | 0.6144 |
85
- | 0.0 | 18.0 | 16632 | 3.7544 | 0.6123 |
86
- | 0.002 | 19.0 | 17556 | 3.7503 | 0.6155 |
87
- | 0.0 | 20.0 | 18480 | 3.7539 | 0.6201 |
88
 
89
 
90
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6614173228346457
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/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.6340
36
+ - Accuracy: 0.6614
37
 
38
  ## Model description
39
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 10
63
 
64
  ### Training results
65
 
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.1476 | 1.0 | 924 | 1.0852 | 0.6394 |
69
+ | 0.8958 | 2.0 | 1848 | 1.0601 | 0.6405 |
70
+ | 0.7798 | 3.0 | 2772 | 0.9798 | 0.6766 |
71
+ | 0.5551 | 4.0 | 3696 | 1.0556 | 0.6720 |
72
+ | 0.4668 | 5.0 | 4620 | 1.2068 | 0.6666 |
73
+ | 0.2422 | 6.0 | 5544 | 1.2924 | 0.6587 |
74
+ | 0.149 | 7.0 | 6468 | 1.4333 | 0.6622 |
75
+ | 0.1688 | 8.0 | 7392 | 1.5455 | 0.6595 |
76
+ | 0.1504 | 9.0 | 8316 | 1.6133 | 0.6617 |
77
+ | 0.0951 | 10.0 | 9240 | 1.6340 | 0.6614 |
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6371d16b5de4f4ec7bb43f08c9989ae7a9464a1ed60b6567d4029e69e6fab5ca
3
  size 343129544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d1a26df134d88a5df9c7a46b8b134d0a64e1f938c64223c8b80d6c14ae83c9
3
  size 343129544
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56a7478b71e1f5d4dc59c68db6526226f5d108e2ffd421741519833598e8800e
3
  size 4704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f99ab836dac8835de80d95ae31a1289d79003fec38f9de6aef64c895fe1c58
3
  size 4704