Model save

README.md

@@ -1,13 +1,11 @@
 ---
-base_model: google/vit-base-patch16-224-in21k
-library_name: peft
+library_name: transformers
 license: apache-2.0
-metrics:
-- accuracy
+base_model: google/vit-base-patch16-224-in21k
 tags:
-- image-classification
-- vision
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: vit-cifar100-cifar100
   results: []
@@ -18,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-cifar100-cifar100
 
-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 cifar100 dataset.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 0.2550
-- Accuracy: 0.9236
+- Loss: 3.1612
+- Accuracy: 0.2223
 
 ## Model description
 
@@ -52,17 +50,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.5206        | 1.0   | 5313  | 0.3323          | 0.9051   |
-| 0.7608        | 2.0   | 10626 | 0.2929          | 0.9139   |
-| 0.8691        | 3.0   | 15939 | 0.2725          | 0.9173   |
-| 0.3582        | 4.0   | 21252 | 0.2581          | 0.9232   |
-| 0.4711        | 5.0   | 26565 | 0.2550          | 0.9236   |
+| 3.7207        | 1.0   | 5313  | 3.8632          | 0.0985   |
+| 3.5093        | 2.0   | 10626 | 3.5664          | 0.1472   |
+| 3.3675        | 3.0   | 15939 | 3.4389          | 0.166    |
+| 2.9505        | 4.0   | 21252 | 3.2326          | 0.2093   |
+| 3.1158        | 5.0   | 26565 | 3.1612          | 0.2223   |
 
 
 ### Framework versions
 
-- PEFT 0.12.0
 - Transformers 4.44.2
 - Pytorch 2.0.1+cu117
 - Datasets 3.0.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1