Noopy
/

train_model_yonsei

Image Classification

Generated from Trainer

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

Noopy commited on Jun 22, 2023

Commit

b718948

·

1 Parent(s): 4451c30

update model card README.md

Files changed (1) hide show

README.md +14 -9

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.889
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 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 cifar10 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6054
-- Accuracy: 0.889
 ## Model description
@@ -60,17 +60,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6193        | 0.99  | 62   | 1.4954          | 0.792    |
-| 0.9245        | 2.0   | 125  | 0.9101          | 0.846    |
-| 0.6781        | 2.99  | 187  | 0.7312          | 0.868    |
-| 0.6326        | 4.0   | 250  | 0.6411          | 0.875    |
-| 0.5272        | 4.96  | 310  | 0.6054          | 0.889    |
 ### Framework versions

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.912
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 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 cifar10 dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.3947
+- Accuracy: 0.912
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.8929        | 0.99  | 62   | 1.7490          | 0.773    |
+| 0.9345        | 2.0   | 125  | 0.8608          | 0.864    |
+| 0.655         | 2.99  | 187  | 0.6876          | 0.866    |
+| 0.5273        | 4.0   | 250  | 0.5422          | 0.904    |
+| 0.4484        | 4.99  | 312  | 0.4926          | 0.893    |
+| 0.4012        | 6.0   | 375  | 0.4887          | 0.892    |
+| 0.353         | 6.99  | 437  | 0.4679          | 0.886    |
+| 0.3711        | 8.0   | 500  | 0.4204          | 0.899    |
+| 0.3079        | 8.99  | 562  | 0.4464          | 0.898    |
+| 0.2955        | 9.92  | 620  | 0.3947          | 0.912    |
 ### Framework versions