JOSEDURANisc
/

vit-model

Image Classification

Generated from Trainer

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

JOSEDURANisc commited on Sep 18, 2023

Commit

9ff0951

·

1 Parent(s): 138a66c

update model card README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -31,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0352
 - Accuracy: 0.9925
 ## Model description
@@ -63,7 +63,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0059        | 3.85  | 500  | 0.0352          | 0.9925   |
 ### Framework versions

 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0223
 - Accuracy: 0.9925
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.1408        | 3.85  | 500  | 0.0223          | 0.9925   |
 ### Framework versions