End of training

README.md

@@ -32,7 +32,7 @@ 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: 0.6614
+- Loss: 0.6830
 - Accuracy: 0.625
 
 ## Model description
@@ -52,7 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 5e-06
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -61,15 +61,17 @@ 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 1    | 0.7041          | 0.625    |
-| No log        | 2.0   | 2    | 0.6657          | 0.625    |
-| No log        | 3.0   | 3    | 0.6614          | 0.625    |
+| No log        | 1.0   | 1    | 0.7019          | 0.5      |
+| No log        | 2.0   | 2    | 0.6880          | 0.625    |
+| No log        | 3.0   | 3    | 0.6830          | 0.625    |
+| No log        | 4.0   | 4    | 0.6885          | 0.5      |
+| No log        | 5.0   | 5    | 0.6830          | 0.625    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44821f01dd35f6caac8c4643c034a3e492efc929a9ba78d9fb5a22da972ee48b
+oid sha256:21e34e89febd47c6a07b8247c53df7814cb1b4959cb177bdc18e39a037708559
 size 343223968