End of training

README.md

@@ -16,8 +16,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4601
-- Wer Score: 1.1378
+- Loss: 0.7051
+- Wer Score: 1.6596
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer Score |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 8.9652        | 10.0  | 50   | 3.5521          | 1.2870    |
-| 4.6095        | 20.0  | 100  | 2.0830          | 1.1944    |
-| 2.3712        | 30.0  | 150  | 1.5451          | 1.1260    |
-| 1.5323        | 40.0  | 200  | 1.4601          | 1.1378    |
+| 0.7017        | 10.0  | 50   | 0.5906          | 1.7247    |
+| 0.2858        | 20.0  | 100  | 0.6435          | 1.6259    |
+| 0.1529        | 30.0  | 150  | 0.6878          | 1.7054    |
+| 0.0987        | 40.0  | 200  | 0.7051          | 1.6596    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e3daf53fb8b711737bd509fe50cdd4f50be7583144716c46cea2bced2e1822
+oid sha256:c4650a172d5b70bb3979f14b276d18387e5fc4a955629bef979544482da13d76
 size 706516040