End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.2463
-- Wer Score: 12.6933
+- Loss: 4.6168
+- Wer Score: 1.7132
 
 ## Model description
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Score |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 3.6923        | 50.0  | 50   | 6.2463          | 12.6933   |
+| 3.2386        | 50.0  | 50   | 4.6168          | 1.7132    |
 
 
 ### Framework versions

runs/May12_19-32-34_93180c600d0f/events.out.tfevents.1715542355.93180c600d0f.7022.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f199ea4ebbca1c089a19c90d8a4cce03b1476405a28717254378cedaa052f009
-size 5560
+oid sha256:21dd5765476f7624e71aa7062d5cb56fad7bcc3bc60d310c7ae412a91f967a0e
+size 5908