End of training

README.md

@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 # donut-base-sroie
 
 This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1461
 
 ## Model description
 
@@ -40,15 +42,27 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 6
+- num_epochs: 10
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.8948        | 1.0   | 45   | 5.7211          |
+| 3.2707        | 2.0   | 90   | 2.8623          |
+| 2.1611        | 3.0   | 135  | 1.7889          |
+| 1.3332        | 4.0   | 180  | 1.4790          |
+| 0.6255        | 5.0   | 225  | 1.3553          |
+| 1.2248        | 6.0   | 270  | 1.2488          |
+| 0.9245        | 7.0   | 315  | 1.1895          |
+| 0.4144        | 8.0   | 360  | 1.2128          |
+| 0.4087        | 9.0   | 405  | 1.1811          |
+| 0.4926        | 10.0  | 450  | 1.1461          |
 
 
 ### Framework versions
 
 - Transformers 4.34.1
-- Pytorch 2.0.1+cu118
+- Pytorch 2.1.0+cu118
 - Datasets 2.14.5
 - Tokenizers 0.14.1