Hugging Face's logo

onizukal
/
Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-large-patch16_fold2

Image Classification
Transformers
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
onizukal commited on
Commit
ed9f593
•
1 Parent(s): 9a5727c

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: 0.6043243243243244
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: 3.9995
36
- - Accuracy: 0.6043
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
- | 1.3721 | 1.0 | 923 | 1.4458 | 0.5151 |
69
- | 1.211 | 2.0 | 1846 | 1.2447 | 0.5646 |
70
- | 1.0199 | 3.0 | 2769 | 1.1676 | 0.5949 |
71
- | 0.647 | 4.0 | 3692 | 1.3168 | 0.5827 |
72
- | 0.663 | 5.0 | 4615 | 1.3702 | 0.6049 |
73
- | 0.4514 | 6.0 | 5538 | 1.7725 | 0.5789 |
74
- | 0.2392 | 7.0 | 6461 | 1.9038 | 0.5757 |
75
- | 0.2501 | 8.0 | 7384 | 2.2880 | 0.5786 |
76
- | 0.2883 | 9.0 | 8307 | 2.4302 | 0.5922 |
77
- | 0.0684 | 10.0 | 9230 | 2.6185 | 0.5822 |
78
- | 0.063 | 11.0 | 10153 | 2.9356 | 0.5814 |
79
- | 0.1381 | 12.0 | 11076 | 3.1443 | 0.5911 |
80
- | 0.0369 | 13.0 | 11999 | 3.4881 | 0.5762 |
81
- | 0.0268 | 14.0 | 12922 | 3.5602 | 0.5816 |
82
- | 0.0267 | 15.0 | 13845 | 3.6681 | 0.6041 |
83
- | 0.028 | 16.0 | 14768 | 3.7330 | 0.5970 |
84
- | 0.0138 | 17.0 | 15691 | 3.9073 | 0.6019 |
85
- | 0.0004 | 18.0 | 16614 | 3.9147 | 0.6 |
86
- | 0.0001 | 19.0 | 17537 | 3.9594 | 0.6030 |
87
- | 0.0 | 20.0 | 18460 | 3.9995 | 0.6043 |
88
 
89
 
90
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6459459459459459
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: 1.6848
36
+ - Accuracy: 0.6459
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
+ | 1.2143 | 1.0 | 923 | 1.1517 | 0.6165 |
69
+ | 0.9069 | 2.0 | 1846 | 1.0496 | 0.6422 |
70
+ | 0.7165 | 3.0 | 2769 | 1.0076 | 0.6576 |
71
+ | 0.4527 | 4.0 | 3692 | 1.0719 | 0.6619 |
72
+ | 0.3647 | 5.0 | 4615 | 1.1978 | 0.6473 |
73
+ | 0.2513 | 6.0 | 5538 | 1.3190 | 0.6570 |
74
+ | 0.1369 | 7.0 | 6461 | 1.4579 | 0.65 |
75
+ | 0.1367 | 8.0 | 7384 | 1.5702 | 0.6543 |
76
+ | 0.0894 | 9.0 | 8307 | 1.6556 | 0.6486 |
77
+ | 0.1414 | 10.0 | 9230 | 1.6848 | 0.6459 |
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab48631d1c92dd0e4e34eaff347e43d5cec279c90ad5d0c4a6d90a202d07dbc8
3
  size 343129544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdaa7233b790cd7597f0c915f9eac5d9b4d6cbac0b3f577d1c8ebef277a3aaae
3
  size 343129544
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21aed2da2e00e361ab38386fe32016b72169da94035bce1b007f7ea73461ff3c
3
  size 4704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7dd39cdfe30cd87667b9de24d735e3cddb5a0ea6f4ee6b3a9cf56698ee155e
3
  size 4704