test

README.md

@@ -17,8 +17,8 @@ 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: 4.3871
-- Accuracy: 0.5
+- Loss: 4.4119
+- Accuracy: 0.4
 
 ## Model description
 
@@ -38,27 +38,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 64
 - 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: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 1    | 4.6565          | 0.0      |
-| No log        | 2.0   | 3    | 4.3871          | 0.5      |
+| No log        | 0.8   | 1    | 4.5809          | 0.05     |
+| No log        | 1.6   | 2    | 4.4119          | 0.4      |
 
 
 ### Framework versions
 
 - Transformers 4.39.3
-- Pytorch 2.1.2
+- Pytorch 2.1.2+cpu
 - Datasets 2.18.0
 - Tokenizers 0.15.2