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 [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2901
-- Accuracy: 0.9167
+- Loss: 0.2542
+- Accuracy: 0.9375
 
 ## Model description
 
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5464        | 0.99  | 36   | 0.4811          | 0.7917   |
-| 0.2194        | 1.99  | 72   | 0.3300          | 0.9167   |
-| 0.2732        | 2.98  | 108  | 0.3896          | 0.875    |
-| 0.057         | 4.0   | 145  | 0.3027          | 0.9167   |
-| 0.0118        | 4.97  | 180  | 0.2901          | 0.9167   |
+| 0.2847        | 0.99  | 36   | 0.2105          | 0.875    |
+| 0.1789        | 1.99  | 72   | 0.3547          | 0.8542   |
+| 0.1312        | 2.98  | 108  | 0.4752          | 0.8542   |
+| 0.059         | 4.0   | 145  | 0.2995          | 0.9375   |
+| 0.0045        | 4.97  | 180  | 0.2542          | 0.9375   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c304b8345b92fb2da28b38f51a9cfae0cf44ec123490f750c6e2861f4695c7d
+oid sha256:3560ea65d3854fc011ae12617d5a739860214030b41c3c1a21a1b58f2dc7dc45
 size 1212799848