Rebecasarai
/

my_awesome_food_model

Image Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Rebecasarai commited on May 22

Commit

b81c8ae

•

1 Parent(s): 8ff3497

End of training

Files changed (1) hide show

README.md +6 -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: 2.9031
-- Accuracy: 0.815
 ## Model description
@@ -46,14 +46,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.4887        | 0.992 | 31   | 3.2930          | 0.798    |
-| 2.9076        | 1.984 | 62   | 2.9031          | 0.815    |
 ### 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: 2.4259
+- Accuracy: 0.85
 ## Model description
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.5408        | 0.992 | 31   | 3.3110          | 0.716    |
+| 2.7272        | 1.984 | 62   | 2.6278          | 0.833    |
+| 2.4426        | 2.976 | 93   | 2.4259          | 0.85     |
 ### Framework versions