Model save

README.md

@@ -1,24 +1,24 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google/vit-base-patch16-224-in21k
+base_model: facebook/convnext-base-224
 tags:
 - generated_from_trainer
 datasets:
 - imagefolder
 model-index:
-- name: vit_model
+- name: convnext_model
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# vit_model
+# convnext_model
 
-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 imagefolder dataset.
+This model is a fine-tuned version of [facebook/convnext-base-224](https://huggingface.co/facebook/convnext-base-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1002
+- Loss: 0.0712
 
 ## Model description
 
@@ -43,15 +43,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1422        | 1.0   | 100  | 0.1418          |
-| 0.0815        | 2.0   | 200  | 0.1324          |
-| 0.0485        | 3.0   | 300  | 0.1002          |
+| 0.0945        | 1.0   | 100  | 0.1009          |
+| 0.0233        | 2.0   | 200  | 0.0851          |
+| 0.0041        | 3.0   | 300  | 0.0755          |
+| 0.0026        | 4.0   | 400  | 0.0715          |
+| 0.0024        | 5.0   | 500  | 0.0712          |
 
 
 ### Framework versions