Model save

README.md

@@ -16,8 +16,8 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4538
-- Accuracy: 0.6788
+- Loss: 1.5517
+- Accuracy: 0.4380
 
 ## Model description
 
@@ -36,7 +36,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 2e-05
 - train_batch_size: 32
 - eval_batch_size: 64
 - seed: 42
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 77   | 1.4538          | 0.6788   |
+| No log        | 1.0   | 77   | 1.5517          | 0.4380   |
 
 
 ### Framework versions
@@ -57,4 +57,4 @@ The following hyperparameters were used during training:
 - Transformers 4.17.0
 - Pytorch 1.10.2+cu113
 - Datasets 1.18.4
-- Tokenizers 0.12.1
+- Tokenizers 0.13.0

eval_results.txt

@@ -1,6 +1,6 @@
 epoch = 1.0
-eval_accuracy = 0.6788321167883211
-eval_loss = 1.4538204669952393
-eval_runtime = 6.6139
-eval_samples_per_second = 41.428
-eval_steps_per_second = 0.756
+eval_accuracy = 0.43795620437956206
+eval_loss = 1.5516855716705322
+eval_runtime = 6.2916
+eval_samples_per_second = 43.55
+eval_steps_per_second = 0.795