End of training

README.md

@@ -18,8 +18,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7185
-- Accuracy: 0.845
+- Loss: 0.3342
+- Accuracy: 0.919
 
 ## Model description
 
@@ -47,15 +47,17 @@ 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: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.8557        | 0.992 | 62   | 2.7283          | 0.761    |
-| 1.9591        | 2.0   | 125  | 1.9040          | 0.833    |
-| 1.6788        | 2.976 | 186  | 1.7185          | 0.845    |
+| 0.2451        | 0.992 | 62   | 0.4081          | 0.906    |
+| 0.1395        | 2.0   | 125  | 0.3829          | 0.905    |
+| 0.1087        | 2.992 | 187  | 0.3393          | 0.919    |
+| 0.0848        | 4.0   | 250  | 0.3120          | 0.927    |
+| 0.1408        | 4.96  | 310  | 0.3342          | 0.919    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a66b4866a285bd842c7d0fd4c1f6b3f14c4ebb51122d2ec71f1b75e9e3dfb6e
+oid sha256:a45023f074268319696e15c31a8bb30fea1f620df2c65915fdda4df97d5633c7
 size 343528508