End of training

README.md

@@ -22,7 +22,7 @@ model-index:
  metrics:
  - name: Accuracy
  type: accuracy
- value: 0.8050847457627118
+ value: 0.809322033898305
 ---
 
 <!-- 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. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.4771
-- Accuracy: 0.8051
+- Loss: 0.5064
+- Accuracy: 0.8093
 
 ## Model description
 
@@ -61,19 +61,20 @@ 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: 0.05
-- num_epochs: 20
+- num_epochs: 25
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4945 | 3.01 | 50 | 0.4621 | 0.7669 |
-| 0.3739 | 6.02 | 100 | 0.4412 | 0.8072 |
-| 0.3005 | 9.02 | 150 | 0.4343 | 0.8008 |
-| 0.2583 | 12.03 | 200 | 0.4364 | 0.8157 |
-| 0.2166 | 15.04 | 250 | 0.4975 | 0.8093 |
-| 0.1874 | 18.05 | 300 | 0.4771 | 0.8051 |
+| 0.4908 | 3.01 | 50 | 0.5141 | 0.7797 |
+| 0.3766 | 6.02 | 100 | 0.4485 | 0.7839 |
+| 0.3121 | 9.02 | 150 | 0.4550 | 0.7903 |
+| 0.2569 | 12.03 | 200 | 0.3977 | 0.8305 |
+| 0.215 | 15.04 | 250 | 0.4732 | 0.7987 |
+| 0.186 | 18.05 | 300 | 0.4804 | 0.8072 |
+| 0.1568 | 21.05 | 350 | 0.5064 | 0.8093 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0653577e10187bb7db9e5fdf76bddf703ee5472ace9d4b1a4afbaf89456e352
+oid sha256:f71be68b33f08a5dbd89e23375c86fe2c0ba53e4c39f5ed6f217a9737c5c56fc
 size 343223968