Trained on ALL, no resize.

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1082
+- Loss: 0.0989
 
 ## Model description
 
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.8821        | 0.0698 | 250  | 0.1363          |
-| 0.132         | 0.1396 | 500  | 0.1163          |
-| 0.1212        | 0.2094 | 750  | 0.1113          |
-| 0.1166        | 0.2792 | 1000 | 0.1082          |
+| 1.0097        | 0.0698 | 250  | 0.1479          |
+| 0.1376        | 0.1396 | 500  | 0.1150          |
+| 0.1178        | 0.2094 | 750  | 0.1041          |
+| 0.1103        | 0.2792 | 1000 | 0.0989          |
 
 
 ### Framework versions

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff1fdf17eae2403ee4d9f013b34b351a35f1a100d2b4e580688fd283f2f363b
+oid sha256:9bad7ffbe89a015773eb3eb9e211b9cd9a910f11d1b9445fcb4962d84898b7da
 size 4999738624

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c5268dd141074ff1b6395d0649fb54cdf724bb978efdd18e56487dd22e5b63
+oid sha256:e3c0360f5e02f6b266aa44f7fe888aad867f5d019dbf281c1c7da78634540520
 size 1658313704