PolizzeDonut-conXLS-3Epochs-20img

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [tedad09/PolizzeDonut-SoloPDF-3Epochs](https://huggingface.co/tedad09/PolizzeDonut-SoloPDF-3Epochs) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7138
+- Loss: 0.3065
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.11          | 1.0   | 10   | 0.8166          |
-| 0.845         | 2.0   | 20   | 0.7362          |
-| 0.8439        | 3.0   | 30   | 0.7138          |
+| 1.1106        | 1.0   | 10   | 0.3138          |
+| 0.843         | 2.0   | 20   | 0.3288          |
+| 0.8708        | 3.0   | 30   | 0.3065          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52adf99dd37e5f1b705a94e3430fa0bfbdb0c9b3b451ee06a60e3b86cbac6373
+oid sha256:a7394e949f111c927c3a03077a5cfd0bb61319017e97201e5b8cf73e64f366b1
 size 809177240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b551c67d932c08dece688cba90dd040f4e0f7893dd58df8460efa5f8d76a586
+oid sha256:9e8a31e1f12ac7ce73239ca68ad2d4f8c2a27fb269c163a1ef64a642946acfac
 size 5048