Elvijs
/

classification_vit_playaround

Generated from Trainer

Model card Files Files and versions Community

Elvijs commited on 18 days ago

Commit

e5a4d09

•

1 Parent(s): 0eaa0ac

End of training

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5927
-- Accuracy: 0.899
 ## Model description
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.688         | 0.992 | 62   | 2.4867          | 0.842    |
-| 1.8591        | 2.0   | 125  | 1.7574          | 0.888    |
-| 1.6524        | 2.976 | 186  | 1.5927          | 0.899    |
 ### 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 an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.6380
+- Accuracy: 0.89
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.7533        | 0.992 | 62   | 2.5753          | 0.83     |
+| 1.8529        | 2.0   | 125  | 1.8001          | 0.865    |
+| 1.5759        | 2.976 | 186  | 1.6380          | 0.89     |
 ### Framework versions