End of training

README.md

@@ -1,5 +1,4 @@
 ---
-license: mit
 tags:
 - generated_from_trainer
 datasets:
@@ -14,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut_pdf_ocr
 
-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.
+This model was trained from scratch on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2879
+- Loss: 0.0560
 
 ## Model description
 
@@ -48,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.7815        | 1.0   | 47   | 2.1495          |
-| 0.6386        | 2.0   | 94   | 0.4316          |
-| 0.336         | 3.0   | 141  | 0.2980          |
-| 0.2021        | 4.0   | 188  | 0.2933          |
-| 0.2655        | 5.0   | 235  | 0.2879          |
+| 0.2417        | 1.0   | 47   | 0.0827          |
+| 0.089         | 2.0   | 94   | 0.0779          |
+| 0.0917        | 3.0   | 141  | 0.0880          |
+| 0.106         | 4.0   | 188  | 0.0533          |
+| 0.1473        | 5.0   | 235  | 0.0560          |
 
 
 ### Framework versions

runs/Apr23_05-17-34_a5c642fecc83/events.out.tfevents.1682227266.a5c642fecc83.542.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d8b08bd76817e171015a641ca313b1c3f4c7b9fa3ebe4a18c4b3688d6f3984
-size 13481
+oid sha256:c13df1b8f620114cf3508e309d1e30f36d8c989e74a20e6b69fffbbbf0ce3113
+size 13835