fjfur10/trocr-cs682-sentences

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/trocr-small-handwritten](https://huggingface.co/microsoft/trocr-small-handwritten) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 12.7579
-- Cer: 1.4663
+- Loss: 18.4189
+- Cer: 2.3451
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Cer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 13.8338       | 1.0   | 14   | 13.0113         | 1.6425 |
-| 12.9341       | 2.0   | 28   | 12.8226         | 1.4922 |
-| 12.655        | 3.0   | 42   | 12.7579         | 1.4663 |
+| 18.267        | 1.0   | 9    | 18.4702         | 2.3908 |
+| 18.5157       | 2.0   | 18   | 18.4523         | 2.3099 |
+| 17.8628       | 3.0   | 27   | 18.4189         | 2.3451 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9855294e8cce63d1de54849139828c5bd856c7e57bb201f4484c0984dbc5c6b
+oid sha256:9c59932f3453bac762dff97f7ec9f34bdeb880b319ee0a9be2b2381d3d36dcd4
 size 246430696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871c983c1927dd0e0dd9f9a560c4a055d71ec2ee373e99c64a5f43940812a5cc
+oid sha256:c6a2afe01e6cfa975e63451dfc3d5bf3d2cb9baf50a3922c168064c39a8e63ca
 size 5240