palicoqiqi/paligemma_ocr_final

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4097
+- Loss: 0.6672
 
 ## Model description
 
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step  | Validation Loss |
-|:-------------:|:------:|:-----:|:---------------:|
-| 0.4327        | 1.0000 | 10099 | 0.4313          |
-| 0.323         | 1.9999 | 20198 | 0.4097          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.9946 | 92   | 0.7563          |
+| No log        | 1.9892 | 184  | 0.6672          |
 
 
 ### Framework versions