End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 1.2679
+- Loss: 2.8819
 
 ## Model description
 
@@ -36,7 +36,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 8.7535        | 0.69  | 50   | 5.1985          |
-| 4.1804        | 1.39  | 100  | 2.1736          |
-| 2.1261        | 2.08  | 150  | 1.3892          |
-| 1.6998        | 2.78  | 200  | 1.2679          |
+| 9.9118        | 0.69  | 50   | 6.5666          |
+| 6.0851        | 1.39  | 100  | 4.2864          |
+| 4.4899        | 2.08  | 150  | 3.3172          |
+| 3.6628        | 2.78  | 200  | 2.8819          |
 
 
 ### Framework versions

runs/Jul07_20-50-03_f4aabf8a5de8/events.out.tfevents.1688763011.f4aabf8a5de8.9489.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab6b44d419f0754ba2c3d0298153679b62e58caa2d009113878dcb07e955a57
-size 10385
+oid sha256:902951259ae971a335897a646e9ff835d81734d8e582d3f7eeef3df88d9e5316
+size 10739